Daily Papers

Visual foundation models have achieved remarkable results in zero-shot image classification and segmentation, but zero-shot change detection remains an open problem. In this paper, we propose the segment any change models (AnyChange), a new type of change detection model that supports zero-shot prediction and generalization on unseen change types and data distributions. AnyChange is built on the segment anything model (SAM) via our training-free adaptation method, bitemporal latent matching. By revealing and exploiting intra-image and inter-image semantic similarities in SAM's latent space, bitemporal latent matching endows SAM with zero-shot change detection capabilities in a training-free way. We also propose a point query mechanism to enable AnyChange's zero-shot object-centric change detection capability. We perform extensive experiments to confirm the effectiveness of AnyChange for zero-shot change detection. AnyChange sets a new record on the SECOND benchmark for unsupervised change detection, exceeding the previous SOTA by up to 4.4% F_1 score, and achieving comparable accuracy with negligible manual annotations (1 pixel per image) for supervised change detection.

Large language model fine-tuning is bottlenecked by memory: a 7B parameter model requires 84GB--14GB for weights, 14GB for gradients, and 56GB for FP32 optimizer states--exceeding even A100-40GB capacity. We present Chronicals, an open-source training framework achieving 3.51x speedup over Unsloth through four synergistic optimizations: (1) fused Triton kernels eliminating 75% of memory traffic via RMSNorm (7x), SwiGLU (5x), and QK-RoPE (2.3x) fusion; (2) Cut Cross-Entropy reducing logit memory from 5GB to 135MB through online softmax computation; (3) LoRA+ with theoretically-derived 16x differential learning rates between adapter matrices; and (4) Best-Fit Decreasing sequence packing recovering 60-75% of compute wasted on padding. On Qwen2.5-0.5B with A100-40GB, Chronicals achieves 41,184 tokens/second for full fine-tuning versus Unsloth's 11,736 tokens/second (3.51x). For LoRA at rank 32, we reach 11,699 tokens/second versus Unsloth MAX's 2,857 tokens/second (4.10x). Critically, we discovered that Unsloth's reported 46,000 tokens/second benchmark exhibited zero gradient norms--the model was not training. We provide complete mathematical foundations: online softmax correctness proofs, FlashAttention IO complexity bounds O(N^2 d^2 M^{-1}), LoRA+ learning rate derivations from gradient magnitude analysis, and bin-packing approximation guarantees. All implementations, benchmarks, and proofs are available at https://github.com/Ajwebdevs/Chronicals with pip installation via https://pypi.org/project/chronicals/.

Clinical machine learning increasingly relies on training corpora generated by large language models (LLMs) rather than annotated by clinicians, and such corpora are described and reused largely on the basis of their reported scale. We test whether volume reflects information content. Analysing the complete output of a multi-agent clinical extraction pipeline applied to 167,034 patient narratives, 2.51 billion generated tokens across the ten text-bearing channels of an eleven-channel pipeline, we introduce Provenance-based Redundancy Decomposition, a token-level classification of the entire output by source. Only 10.9% of the output is trainable-unique content while 79.4% is redundant; raw token count overstates information content by roughly ninefold. The redundancy arises through two distinct mechanisms, verbatim copying of source context into per-item fields, and duplication of generated text across records, of which only the former is losslessly removable. An independent, model-free analysis based on lossless compression confirms the redundancy, recovering the two mechanisms without reference to the provenance labels. One pipeline channel carries almost no redundancy, showing that the level of redundancy depends on how each channel is structured rather than being a fixed property of LLM extraction. Because uncorrected redundancy up-weights the longer, more complex presentations that generate the most items, it skews the token-level training distribution of the corpus, a property we measure directly. In a controlled downstream test, de-duplicating the corpus before adaptation improved a clinical encoder on external disease-recognition benchmarks at equal token budget, robustly across adaptation depths and replicated on a second benchmark, confirming that the redundancy carries a measurable cost beyond storage. The classification tool is released openly.

Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images or short clips, we identify that they fail to mitigate drift in extended sequences due to unstable reward landscapes and the hypersensitivity of distilled parameters. To overcome these limitations, we introduce Test-Time Correction (TTC), a training-free alternative. Specifically, TTC utilizes the initial frame as a stable reference anchor to calibrate intermediate stochastic states along the sampling trajectory. Extensive experiments demonstrate that our method seamlessly integrates with various distilled models, extending generation lengths with negligible overhead while matching the quality of resource-intensive training-based methods on 30-second benchmarks.

Video-to-audio (V2A) generation is important for video editing and post-processing, enabling the creation of semantics-aligned audio for silent video. However, most existing methods focus on generating short-form audio for short video segment (less than 10 seconds), while giving little attention to the scenario of long-form video inputs. For current UNet-based diffusion V2A models, an inevitable problem when handling long-form audio generation is the inconsistencies within the final concatenated audio. In this paper, we first highlight the importance of long-form V2A problem. Besides, we propose LoVA, a novel model for Long-form Video-to-Audio generation. Based on the Diffusion Transformer (DiT) architecture, LoVA proves to be more effective at generating long-form audio compared to existing autoregressive models and UNet-based diffusion models. Extensive objective and subjective experiments demonstrate that LoVA achieves comparable performance on 10-second V2A benchmark and outperforms all other baselines on a benchmark with long-form video input.

Language acquisition is vital to revealing the nature of human language intelligence and has recently emerged as a promising perspective for improving the interpretability of large language models (LLMs). However, it is ethically and practically infeasible to conduct experiments that require controlling human learners' language inputs. This poses challenges for the verifiability and scalability of language acquisition modeling, particularly in Chinese second language acquisition (SLA). While LLMs provide a controllable and reproducible alternative, a systematic benchmark to support phase-wise modeling and assessment is still lacking. In this paper, we present HSKBenchmark, the first benchmark for staged modeling and writing assessment of LLMs in Chinese SLA. It covers HSK levels 3 to 6 and includes authentic textbooks with 6.76 million tokens, 16K synthetic instruction samples, 30 test topics, and a linguistically grounded evaluation system. To simulate human learning trajectories, we introduce a curriculum-tuning framework that trains models from beginner to advanced levels. An evaluation system is created to examine level-based grammar coverage, writing errors, lexical and syntactic complexity, and holistic scoring. We also build HSKAgent, fine-tuned on 10K learner compositions. Extensive experimental results demonstrate that HSKBenchmark not only models Chinese SLA effectively, but also serves as a reliable benchmark for dynamic writing assessment in LLMs. Our fine-tuned LLMs have writing performance on par with advanced human learners and exhibit human-like acquisition characteristics. The HSKBenchmark, HSKAgent, and checkpoints serve as foundational tools and resources, with the potential to pave the way for future research on language acquisition modeling and LLMs interpretability. Code and data are publicly available at: https://github.com/CharlesYang030/HSKB.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, with code generation emerging as a key area of focus. While numerous benchmarks have been proposed to evaluate their code generation abilities, these benchmarks face several critical limitations. First, they often rely on manual annotations, which are time-consuming and difficult to scale across different programming languages and problem complexities. Second, most existing benchmarks focus primarily on Python, while the few multilingual benchmarks suffer from limited difficulty and uneven language distribution. To address these challenges, we propose AutoCodeGen, an automated method for generating high-difficulty multilingual code generation datasets without manual annotations. AutoCodeGen ensures the correctness and completeness of test cases by generating test inputs with LLMs and obtaining test outputs through a multilingual sandbox, while achieving high data quality through reverse-order problem generation and multiple filtering steps. Using this novel method, we introduce AutoCodeBench, a large-scale code generation benchmark comprising 3,920 problems evenly distributed across 20 programming languages. It is specifically designed to evaluate LLMs on challenging, diverse, and practical multilingual tasks. We evaluate over 30 leading open-source and proprietary LLMs on AutoCodeBench and its simplified version AutoCodeBench-Lite. The results show that even the most advanced LLMs struggle with the complexity, diversity, and multilingual nature of these tasks. Besides, we introduce AutoCodeBench-Complete, specifically designed for base models to assess their few-shot code generation capabilities. We hope the AutoCodeBench series will serve as a valuable resource and inspire the community to focus on more challenging and practical multilingual code generation scenarios.

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet their widespread adoption remains constrained by the lack of a standardized and efficient inference framework. We present dInfer, an efficient and extensible framework for dLLM inference. dInfer decomposes the inference pipeline into four modular components--model, diffusion iteration manager, decoding strategy, and KV-cache manager--and integrates novel algorithms for each component alongside system-level optimizations. Through this combination of algorithmic innovations and system enhancements, dInfer achieves substantial efficiency gains without compromising output quality on LLaDA-MoE. At batch size 1, it surpasses 1,100 tokens per second on HumanEval and averages over 800 tokens per second across six benchmarks on 8times H800 GPUs. Compared to prior systems, dInfer delivers a 10times speedup over Fast-dLLM while maintaining similar model performance. Even compared to the AR model (with a comparable number of activation parameters and performance) QWen2.5-3B, which is highly optimized with the latest vLLM inference engine, dInfer still delivers a 2-3times speedup. The implementation of dInfer is open-sourced at https://github.com/inclusionAI/dInfer.

Recent frontier models employ long chain-of-thought reasoning to explore solution spaces in context and achieve stonger performance. While many works study distillation to build smaller yet capable models, most focus on English and little is known about language-specific reasoning. To bridge this gap, we first introduct **Language-Mixed CoT**, a reasoning schema that switches between English and a target language, using English as an anchor to excel in reasoning while minimizing translation artificats. As a Korean case study, we curate **Yi-Sang**: 5.79M native-Korean prompts from web Q&A, exams, STEM, and code; 3.7M long reasoning traces generated from Qwen3-32B; and a targeted 260k high-yield subset. We train ninve models (4B-35B) across six families (Qwen2.5, Llama-3.1, Gemma-3, etc). Our best model, **KO-REAson-35B**, achieves state-of-the-art performance, with the highest overall average score (64.0 \pm 25), ranking first on 5/9 benchmarks and second on the remainder. Samller and mid-sized models also benefit substantially, with an average improvement of +18.6 points across teh evaluated nine benchmarks. Ablations show **Language-Mixed CoT** is more effective than monolingual CoT, also resulting in cross-lingual and mult-modal performance gains. We release our data-curation pipeline, evaluation system, datasets, and models to advance research on language-specific reasoning. Data and model collection: https://huggingface.co/KOREAson.

Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language learning and assessment. Crucially, L2-Bench measures model performativity on the application of learning experience design principles rather than mere knowledge of those principles or broad learning outcomes. Our contributions include: (1) a validated taxonomy of 12 competencies and 31 subcompetencies validated by 200+ expert practitioners (task authenticity: 4.42/5.00, criteria adequacy: 4.18/5.00); (2) a rubric-based evaluation methodology that we believe can, if adapted, generalize to similar (open-ended, qualitative) disciplines; (3) an evaluation dataset that produces reliable signal about model strengths, weaknesses, and contextual robustness across diverse L2 education scenarios. We find that, among large models, Claude Opus 4.7 performs best overall (85.5%), though is marginally outperformed on several constituent tasks. We also find that performance drops notably on harder tasks (69.9% to 73.4%). L2-Bench provides education stakeholders better methods to make more informed decisions about real-world AIED adoption, use, and governance, while advancing the maturing science of AI evaluations for education.

Out-of-distribution (OOD) detection is a task that detects OOD samples during inference to ensure the safety of deployed models. However, conventional benchmarks have reached performance saturation, making it difficult to compare recent OOD detection methods. To address this challenge, we introduce three novel OOD detection benchmarks that enable a deeper understanding of method characteristics and reflect real-world conditions. First, we present ImageNet-X, designed to evaluate performance under challenging semantic shifts. Second, we propose ImageNet-FS-X for full-spectrum OOD detection, assessing robustness to covariate shifts (feature distribution shifts). Finally, we propose Wilds-FS-X, which extends these evaluations to real-world datasets, offering a more comprehensive testbed. Our experiments reveal that recent CLIP-based OOD detection methods struggle to varying degrees across the three proposed benchmarks, and none of them consistently outperforms the others. We hope the community goes beyond specific benchmarks and includes more challenging conditions reflecting real-world scenarios. The code is https://github.com/hoshi23/OOD-X-Benchmarks.

Large language models (LLMs) have proven invaluable for code generation, particularly in interactive settings. However, existing code generation benchmarks fail to capture the diverse feedback encountered in multi-turn interactions, limiting our ability to evaluate LLMs in these contexts. To address this gap, we present a set of novel benchmarks that explicitly model the quality of feedback provided to code generation LLMs. Our contributions are threefold: First, we introduce CONVCODEWORLD, a novel and reproducible environment for benchmarking interactive code generation. CONVCODEWORLD simulates 9 distinct interactive code generation scenarios while systematically combining three types of feedback: (a) compilation feedback; (b) execution feedback with varying test coverage; (c) verbal feedback generated by GPT-4o with different levels of expertise. Second, we introduce CONVCODEBENCH, a fast, static version of benchmark that uses pre-generated feedback logs, eliminating the need for costly dynamic verbal feedback generation while maintaining strong Spearman's rank correlations (0.82 to 0.99) with CONVCODEWORLD. Third, extensive evaluations of both closed-source and open-source LLMs including R1-Distill on CONVCODEWORLD reveal key insights: (a) LLM performance varies significantly based on the feedback provided; (b) Weaker LLMs, with sufficient feedback, can outperform single-turn results of state-of-the-art LLMs without feedback; (c) Training on a specific feedback combination can limit an LLM's ability to utilize unseen combinations; (d) LLMs solve problems in fewer turns (high MRR) may not solve as many problems overall (high Recall), and vice versa. All implementations and benchmarks will be made publicly available at https://huggingface.co/spaces/ConvCodeWorld/ConvCodeWorld

RNA plays a pivotal role in translating genetic instructions into functional outcomes, underscoring its importance in biological processes and disease mechanisms. Despite the emergence of numerous deep learning approaches for RNA, particularly universal RNA language models, there remains a significant lack of standardized benchmarks to assess the effectiveness of these methods. In this study, we introduce the first comprehensive RNA benchmark BEACON (BEnchmArk for COmprehensive RNA Task and Language Models). First, BEACON comprises 13 distinct tasks derived from extensive previous work covering structural analysis, functional studies, and engineering applications, enabling a comprehensive assessment of the performance of methods on various RNA understanding tasks. Second, we examine a range of models, including traditional approaches like CNNs, as well as advanced RNA foundation models based on language models, offering valuable insights into the task-specific performances of these models. Third, we investigate the vital RNA language model components from the tokenizer and positional encoding aspects. Notably, our findings emphasize the superiority of single nucleotide tokenization and the effectiveness of Attention with Linear Biases (ALiBi) over traditional positional encoding methods. Based on these insights, a simple yet strong baseline called BEACON-B is proposed, which can achieve outstanding performance with limited data and computational resources. The datasets and source code of our benchmark are available at https://github.com/terry-r123/RNABenchmark.

Among existing online mobile-use benchmarks, AndroidWorld has emerged as the dominant benchmark due to its reproducible environment and deterministic evaluation; however, recent agents achieving over 90% success rates indicate its saturation and motivate the need for a more challenging benchmark. In addition, its environment lacks key application categories, such as e-commerce and enterprise communication, and does not reflect realistic mobile-use scenarios characterized by vague user instructions and hybrid tool usage. To bridge this gap, we introduce MobileWorld, a substantially more challenging benchmark designed to better reflect real-world mobile usage, comprising 201 tasks across 20 applications, while maintaining the same level of reproducible evaluation as AndroidWorld. The difficulty of MobileWorld is twofold. First, it emphasizes long-horizon tasks with cross-application interactions: MobileWorld requires nearly twice as many task-completion steps on average (27.8 vs. 14.3) and includes far more multi-application tasks (62.2% vs. 9.5%) compared to AndroidWorld. Second, MobileWorld extends beyond standard GUI manipulation by introducing novel task categories, including agent-user interaction and MCP-augmented tasks. To ensure robust evaluation, we provide snapshot-based container environment and precise functional verifications, including backend database inspection and task callback APIs. We further develop a planner-executor agentic framework with extended action spaces to support user interactions and MCP calls. Our results reveal a sharp performance drop compared to AndroidWorld, with the best agentic framework and end-to-end model achieving 51.7% and 20.9% success rates, respectively. Our analysis shows that current models struggle significantly with user interaction and MCP calls, offering a strategic roadmap toward more robust, next-generation mobile intelligence.

Low-rank adaptation (LoRA) methods show great potential for scaling pre-trained general-purpose Large Language Models (LLMs) to hundreds or thousands of use scenarios. However, their efficacy in high-stakes domains like finance is rarely explored, e.g., passing CFA exams and analyzing SEC filings. In this paper, we present the open-source FinLoRA project that benchmarks LoRA methods on both general and highly professional financial tasks. First, we curated 19 datasets covering diverse financial applications; in particular, we created four novel XBRL analysis datasets based on 150 SEC filings. Second, we evaluated five LoRA methods and five base LLMs. Finally, we provide extensive experimental results in terms of accuracy, F1, and BERTScore and report computational cost in terms of time and GPU memory during fine-tuning and inference stages. We find that LoRA methods achieved substantial performance gains of 36\% on average over base models. Our FinLoRA project provides an affordable and scalable approach to democratize financial intelligence to the general public. Datasets, LoRA adapters, code, and documentation are available at https://github.com/Open-Finance-Lab/FinLoRA

Text-to-SQL enables users to interact with databases using natural language, simplifying the retrieval and synthesis of information. Despite the remarkable success of large language models (LLMs) in translating natural language questions into SQL queries, widespread deployment remains limited due to two primary challenges. First, the effective use of text-to-SQL models depends on users' understanding of the model's capabilities-the scope of questions the model can correctly answer. Second, the absence of abstention mechanisms can lead to incorrect SQL generation going unnoticed, thereby undermining trust in the model's output. To enable wider deployment, it is crucial to address these challenges in model design and enhance model evaluation to build trust in the model's output. To this end, we introduce TrustSQL, a novel comprehensive benchmark designed to evaluate text-to-SQL reliability-defined as a model's ability to correctly handle any type of input question by generating correct SQL queries for feasible questions and abstaining from generating infeasible ones (e.g., due to schema incompatibility or functionalities beyond SQL). We evaluate existing methods using a novel penalty-based scoring metric with two modeling approaches: (1) pipeline-based methods combining SQL generators with infeasible question detectors and SQL error detectors for abstention; and (2) unified methods using a single model for the entire task. Our experimental results reveal that achieving high scores under severe penalties requires significant effort and provide a new perspective on developing text-to-SQL models for safer deployment. TrustSQL is available at https://github.com/glee4810/TrustSQL.

Manual peripheral blood smear (PBS) analysis is labor intensive and subjective. While deep learning offers a promising alternative, a systematic evaluation of state of the art models such as YOLOv11 for fine grained PBS detection is still lacking. In this work, we make two key contributions. First, we curate a large scale annotated dataset for blood cell detection and classification, comprising 16,891 images across 12 peripheral blood cell (PBC) classes, along with the red blood cell class, all carefully re annotated for object detection tasks. In total, the dataset contains 298,850 annotated cells. Second, we leverage this dataset to conduct a comprehensive evaluation of five YOLOv11 variants (ranging from Nano to XLarge). These models are rigorously benchmarked under two data splitting strategies (70:20:10 and 80:10:10) and systematically assessed using multiple performance criteria, including mean Average Precision (mAP), precision, recall, F1 score, and computational efficiency. Our experiments show that the YOLOv11 Medium variant achieves the best trade off, reaching a mAP@0.5 of 0.934 under the 8:1:1 split. Larger models (Large and XLarge) provide only marginal accuracy gains at substantially higher computational cost. Moreover, the 8:1:1 split consistently outperforms the 7:2:1 split across all models. These findings highlight YOLOv11, particularly the Medium variant, as a highly effective framework for automated, fine grained PBS detection. Beyond benchmarking, our publicly released dataset (github.com/Mohamad-AbouAli/OI-PBC-Dataset) offers a valuable resource to advance research on blood cell detection and classification in hematology.

Phone call transcript labeling is prohibitively expensive (approximately 2 USD per minute) due to privacy regulations, consent requirements, and manual annotation costs requiring 3 hours of expert time per hour of audio. Existing extraction methods fail on conversational speech containing disfluencies, interruptions, and speaker overlap. We introduce LingVarBench, a synthetic data generation pipeline that addresses these constraints through automated validation. First, we prompt an LLM to generate realistic structured field values across multiple use cases. Second, we recursively prompt the model to transform these values into thousands of natural conversational utterances containing typical phone call characteristics. Third, we validate each synthetic utterance by testing whether a separate LLM-based extractor can recover the original structured information. We employ DSPy's SIMBA optimizer to automatically synthesize extraction prompts from validated synthetic transcripts, eliminating manual prompt engineering. Our optimized prompts achieve up to 95 percent accuracy for numeric fields (vs. 88-89 percent zero-shot), 90 percent for names (vs. 47-79 percent), and over 80 percent for dates (vs. 72-77 percent) on real customer transcripts, demonstrating substantial gains over zero-shot prompting. The synthetic-to-real transfer demonstrates that conversational patterns learned from generated data generalize effectively to authentic phone calls containing background noise and domain-specific terminology. LingVarBench provides the first systematic benchmark for structured extraction from synthetic conversational data, demonstrating that automated prompt optimization overcomes cost and privacy barriers preventing large-scale phone call analysis in commercial settings.

In recent years, several efforts have been aimed at improving the robustness of vision models to domains and environments unseen during training. An important practical problem pertains to models deployed in a new geography that is under-represented in the training dataset, posing a direct challenge to fair and inclusive computer vision. In this paper, we study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation containing benchmarks across diverse tasks like scene recognition (GeoPlaces), image classification (GeoImNet) and universal adaptation (GeoUniDA). Second, we investigate the nature of distribution shifts typical to the problem of geographic adaptation and hypothesize that the major source of domain shifts arise from significant variations in scene context (context shift), object design (design shift) and label distribution (prior shift) across geographies. Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures on GeoNet, showing that they do not suffice for geographical adaptation, and that large-scale pre-training using large vision models also does not lead to geographic robustness. Our dataset is publicly available at https://tarun005.github.io/GeoNet.

Due to the high computational demands executing a rigorous comparison between hyperparameter optimization (HPO) methods is often cumbersome. The goal of this paper is to facilitate a better empirical evaluation of HPO methods by providing benchmarks that are cheap to evaluate, but still represent realistic use cases. We believe these benchmarks provide an easy and efficient way to conduct reproducible experiments for neural hyperparameter search. Our benchmarks consist of a large grid of configurations of a feed forward neural network on four different regression datasets including architectural hyperparameters and hyperparameters concerning the training pipeline. Based on this data, we performed an in-depth analysis to gain a better understanding of the properties of the optimization problem, as well as of the importance of different types of hyperparameters. Second, we exhaustively compared various different state-of-the-art methods from the hyperparameter optimization literature on these benchmarks in terms of performance and robustness.

Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, evaluating these visual and textual search abilities is still difficult, and existing benchmarks have two major limitations. First, existing benchmarks are not visual search-centric: answers that should require visual search are often leaked through cross-textual cues in the text questions or can be inferred from the prior world knowledge in current MLLMs. Second, overly idealized evaluation scenario: On the image-search side, the required information can often be obtained via near-exact matching against the full image, while the text-search side is overly direct and insufficiently challenging. To address these issues, we construct the Vision-DeepResearch benchmark (VDR-Bench) comprising 2,000 VQA instances. All questions are created via a careful, multi-stage curation pipeline and rigorous expert review, designed to assess the behavior of Vision-DeepResearch systems under realistic real-world conditions. Moreover, to address the insufficient visual retrieval capabilities of current MLLMs, we propose a simple multi-round cropped-search workflow. This strategy is shown to effectively improve model performance in realistic visual retrieval scenarios. Overall, our results provide practical guidance for the design of future multimodal deep-research systems. The code will be released in https://github.com/Osilly/Vision-DeepResearch.

Benchmarks that closely reflect downstream application scenarios are essential for the streamlined adoption of new research in tabular machine learning (ML). In this work, we examine existing tabular benchmarks and find two common characteristics of industry-grade tabular data that are underrepresented in the datasets available to the academic community. First, tabular data often changes over time in real-world deployment scenarios. This impacts model performance and requires time-based train and test splits for correct model evaluation. Yet, existing academic tabular datasets often lack timestamp metadata to enable such evaluation. Second, a considerable portion of datasets in production settings stem from extensive data acquisition and feature engineering pipelines. For each specific dataset, this can have a different impact on the absolute and relative number of predictive, uninformative, and correlated features, which in turn can affect model selection. To fill the aforementioned gaps in academic benchmarks, we introduce TabReD -- a collection of eight industry-grade tabular datasets covering a wide range of domains from finance to food delivery services. We assess a large number of tabular ML models in the feature-rich, temporally-evolving data setting facilitated by TabReD. We demonstrate that evaluation on time-based data splits leads to different methods ranking, compared to evaluation on random splits more common in academic benchmarks. Furthermore, on the TabReD datasets, MLP-like architectures and GBDT show the best results, while more sophisticated DL models are yet to prove their effectiveness.

Large vision-language models (LVLMs) have demonstrated remarkable achievements, yet the generation of non-factual responses remains prevalent in fact-seeking question answering (QA). Current multimodal fact-seeking benchmarks primarily focus on comparing model outputs to ground truth answers, providing limited insights into the performance of modality-specific modules. To bridge this gap, we introduce VisualSimpleQA, a multimodal fact-seeking benchmark with two key features. First, it enables streamlined and decoupled evaluation of LVLMs in visual and linguistic modalities. Second, it incorporates well-defined difficulty criteria to guide human annotation and facilitates the extraction of a challenging subset, VisualSimpleQA-hard. Experiments on 15 LVLMs show that even state-of-the-art models such as GPT-4o achieve merely 60%+ correctness in multimodal fact-seeking QA on VisualSimpleQA and 30%+ on VisualSimpleQA-hard. Furthermore, the decoupled evaluation across these models highlights substantial opportunities for improvement in both visual and linguistic modules. The dataset is available at https://huggingface.co/datasets/WYLing/VisualSimpleQA.

We present CRUXEval (Code Reasoning, Understanding, and eXecution Evaluation), a benchmark consisting of 800 Python functions (3-13 lines). Each function comes with an input-output pair, leading to two natural tasks: input prediction and output prediction. First, we propose a generic recipe for generating our execution benchmark which can be used to create future variation of the benchmark. Second, we evaluate twenty code models on our benchmark and discover that many recent high-scoring models on HumanEval do not show the same improvements on our benchmark. Third, we show that simple CoT and fine-tuning schemes can improve performance on our benchmark but remain far from solving it. The best setup, GPT-4 with chain of thought (CoT), achieves a pass@1 of 75% and 81% on input and output prediction, respectively. In contrast, Code Llama 34B achieves a pass@1 of 50% and 46% on input and output prediction, highlighting the gap between open and closed source models. As no model is close to acing CRUXEval, we provide examples of consistent GPT-4 failures on simple programs as a lens into its code reasoning capabilities and areas for improvement.

Robust benchmarks are crucial for evaluating Multimodal Large Language Models (MLLMs). Yet we find that models can ace many multimodal benchmarks without strong visual understanding, instead exploiting biases, linguistic priors, and superficial patterns. This is especially problematic for vision-centric benchmarks that are meant to require visual inputs. We adopt a diagnostic principle for benchmark design: if a benchmark can be gamed, it will be. Designers should therefore try to ``game'' their own benchmarks first, using diagnostic and debiasing procedures to systematically identify and mitigate non-visual biases. Effective diagnosis requires directly ``training on the test set'' -- probing the released test set for its intrinsic, exploitable patterns. We operationalize this standard with two components. First, we diagnose benchmark susceptibility using a ``Test-set Stress-Test'' (TsT) methodology. Our primary diagnostic tool involves fine-tuning a powerful Large Language Model via k-fold cross-validation on exclusively the non-visual, textual inputs of the test set to reveal shortcut performance and assign each sample a bias score s(x). We complement this with a lightweight Random Forest-based diagnostic operating on hand-crafted features for fast, interpretable auditing. Second, we debias benchmarks by filtering high-bias samples using an ``Iterative Bias Pruning'' (IBP) procedure. Applying this framework to four benchmarks -- VSI-Bench, CV-Bench, MMMU, and VideoMME -- we uncover pervasive non-visual biases. As a case study, we apply our full framework to create VSI-Bench-Debiased, demonstrating reduced non-visual solvability and a wider vision-blind performance gap than the original.

Most current end-to-end (E2E) autonomous driving algorithms are built on standard vehicles in structured transportation scenarios, lacking exploration of robot navigation for unstructured scenarios such as auxiliary roads, campus roads, and indoor settings. This paper investigates E2E robot navigation in unstructured road environments. First, we introduce two data collection pipelines - one for real-world robot data and another for synthetic data generated using the Isaac Sim simulator, which together produce an unstructured robotics navigation dataset -- FreeWorld Dataset. Second, we fine-tuned an efficient E2E autonomous driving model -- VAD -- using our datasets to validate the performance and adaptability of E2E autonomous driving models in these environments. Results demonstrate that fine-tuning through our datasets significantly enhances the navigation potential of E2E autonomous driving models in unstructured robotic environments. Thus, this paper presents the first dataset targeting E2E robot navigation tasks in unstructured scenarios, and provides a benchmark based on vision-based E2E autonomous driving algorithms to facilitate the development of E2E navigation technology for logistics and service robots. The project is available on Github.

This paper introduces a novel human pose estimation benchmark, Human Pose with Millimeter Wave Radar (HuPR), that includes synchronized vision and radio signal components. This dataset is created using cross-calibrated mmWave radar sensors and a monocular RGB camera for cross-modality training of radar-based human pose estimation. There are two advantages of using mmWave radar to perform human pose estimation. First, it is robust to dark and low-light conditions. Second, it is not visually perceivable by humans and thus, can be widely applied to applications with privacy concerns, e.g., surveillance systems in patient rooms. In addition to the benchmark, we propose a cross-modality training framework that leverages the ground-truth 2D keypoints representing human body joints for training, which are systematically generated from the pre-trained 2D pose estimation network based on a monocular camera input image, avoiding laborious manual label annotation efforts. The framework consists of a new radar pre-processing method that better extracts the velocity information from radar data, Cross- and Self-Attention Module (CSAM), to fuse multi-scale radar features, and Pose Refinement Graph Convolutional Networks (PRGCN), to refine the predicted keypoint confidence heatmaps. Our intensive experiments on the HuPR benchmark show that the proposed scheme achieves better human pose estimation performance with only radar data, as compared to traditional pre-processing solutions and previous radio-frequency-based methods.

When a benchmark's accuracy saturates, it is often retired and replaced with a more challenging version. We show that this approach privileges accuracy and misses the opportunity to study six other key dimensions of agent performance: construct validity issues such as shortcuts, out-of-distribution generalizability, efficiency, reliability, the relative importance of the model versus the scaffold, and uplift from human-agent collaboration. We use CORE-Bench Hard, a benchmark for computational reproducibility of scientific code, as a case study to demonstrate that measuring agents along these dimensions yields meaningful insights into agent performance even after accuracy saturates. First, we surface threats to construct validity in CORE-Bench Hard that are difficult to anticipate with less capable agents. We introduce an improved benchmark, CORE-Bench v1.1, and an out-of-distribution task suite, CORE-Bench OOD. Second, we find that despite accuracy saturation, CORE-Bench v1.1 remains useful for measuring efficiency, reliability, model performance, and scaffold performance. Finally, we conduct a small-scale randomized experiment to measure uplift from human-agent collaboration on real-world computational reproducibility tasks. We find a statistically significant speedup by about a factor of two -- likely underestimated due to one-fifth of human-only reproductions reaching the time limit before completing -- and describe various other findings. Together, our contributions present a more rigorous alternative to the dominant accuracy-centric evaluation paradigm.

While large audio language models (LALMs) have achieved remarkable progress in audio processing at the second- or minute-level scale, understanding hour-level audio remains a fundamental bottleneck. Existing benchmarks predominantly rely on short clips or artificially concatenated segments, failing to faithfully assess LALM capacity for long-range information comprehension in real-world scenarios such as podcasts and lengthy speeches. To address this gap, we introduce VoiceGiraffe, a novel benchmark designed to rigorously evaluate LALMs across diverse real-world scenarios, modalities, and languages under long-context settings. It comprises 1500 curated triplets structured into a dual-level taxonomy of single-hop perception and multi-hop reasoning. We evaluate a broad suite of open-source and proprietary LALMs against human performance. Results underscore three fundamental findings. First, VoiceGiraffe remains highly challenging and far from saturation. Second, we show that no single inference paradigm universally dominates. The E2E inference benefits models with native long-context audio understanding, cascaded caption aggregation stabilizes small models overwhelmed by hour-scale audio, and reasoning-enhanced cascading with external LLM helps weaker models but can bottleneck stronger proprietary systems. Third, we reveal long-range memory persistence as a key bottleneck. LALMs are better at answering questions that require connecting salient causal cues than those requiring sustained tracking of sparse events across long audio, whereas humans show the opposite pattern. These findings position VoiceGiraffe as a challenging and diagnostic testbed for long-form audio understanding, highlighting the need for LALMs with persistent memory and robust long-range aggregation.

Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are primarily constructed from high-quality images captured under idealized conditions. This raises a critical question: when visual cues are severely degraded by adverse weather conditions such as rain, snow, or fog, can VLMs sustain reliable reasoning segmentation capabilities? In response to this challenge, we introduce WeatherReasonSeg, a benchmark designed to evaluate VLM performance in reasoning-based segmentation under adverse weather conditions. It consists of two complementary components. First, we construct a controllable reasoning dataset by applying synthetic weather with varying severity levels to existing segmentation datasets, enabling fine-grained robustness analysis. Second, to capture real-world complexity, we curate a real-world adverse-weather reasoning segmentation dataset with semantically consistent queries generated via mask-guided LLM prompting. We further broaden the evaluation scope across five reasoning dimensions, including functionality, application scenarios, structural attributes, interactions, and requirement matching. Extensive experiments across diverse VLMs reveal two key findings: (1) VLM performance degrades monotonically with increasing weather severity, and (2) different weather types induce distinct vulnerability patterns. We hope WeatherReasonSeg will serve as a foundation for advancing robust, weather-aware reasoning.

Flicker artifacts in short-exposure images are caused by the interplay between the row-wise exposure mechanism of rolling shutter cameras and the temporal intensity variations of alternating current (AC)-powered lighting. These artifacts typically appear as uneven brightness distribution across the image, forming noticeable dark bands. Beyond compromising image quality, this structured noise also affects high-level tasks, such as object detection and tracking, where reliable lighting is crucial. Despite the prevalence of flicker, the lack of a large-scale, realistic dataset has been a significant barrier to advancing research in flicker removal. To address this issue, we present BurstDeflicker, a scalable benchmark constructed using three complementary data acquisition strategies. First, we develop a Retinex-based synthesis pipeline that redefines the goal of flicker removal and enables controllable manipulation of key flicker-related attributes (e.g., intensity, area, and frequency), thereby facilitating the generation of diverse flicker patterns. Second, we capture 4,000 real-world flicker images from different scenes, which help the model better understand the spatial and temporal characteristics of real flicker artifacts and generalize more effectively to wild scenarios. Finally, due to the non-repeatable nature of dynamic scenes, we propose a green-screen method to incorporate motion into image pairs while preserving real flicker degradation. Comprehensive experiments demonstrate the effectiveness of our dataset and its potential to advance research in flicker removal.

Root cause analysis (RCA) for microservice systems has gained significant attention in recent years. However, there is still no standard benchmark that includes large-scale datasets and supports comprehensive evaluation environments. In this paper, we introduce RCAEval, an open-source benchmark that provides datasets and an evaluation environment for RCA in microservice systems. First, we introduce three comprehensive datasets comprising 735 failure cases collected from three microservice systems, covering various fault types observed in real-world failures. Second, we present a comprehensive evaluation framework that includes fifteen reproducible baselines covering a wide range of RCA approaches, with the ability to evaluate both coarse-grained and fine-grained RCA. We hope that this ready-to-use benchmark will enable researchers and practitioners to conduct extensive analysis and pave the way for robust new solutions for RCA of microservice systems.

Indian Sign Language has limited resources for developing machine learning and data-driven approaches for automated language processing. Though text/audio-based language processing techniques have shown colossal research interest and tremendous improvements in the last few years, Sign Languages still need to catch up due to the need for more resources. To bridge this gap, in this work, we propose iSign: a benchmark for Indian Sign Language (ISL) Processing. We make three primary contributions to this work. First, we release one of the largest ISL-English datasets with more than 118K video-sentence/phrase pairs. To the best of our knowledge, it is the largest sign language dataset available for ISL. Second, we propose multiple NLP-specific tasks (including SignVideo2Text, SignPose2Text, Text2Pose, Word Prediction, and Sign Semantics) and benchmark them with the baseline models for easier access to the research community. Third, we provide detailed insights into the proposed benchmarks with a few linguistic insights into the workings of ISL. We streamline the evaluation of Sign Language processing, addressing the gaps in the NLP research community for Sign Languages. We release the dataset, tasks, and models via the following website: https://exploration-lab.github.io/iSign/

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of benchmarks involve Python, while only 5 benchmarks involve Java. Second, imbalanced code granularity. Function-/statement-level benchmarks account for over 83.3% of benchmarks. Only a mere handful extends to class-/project-levels, and all are limited to Python. Third, lacking advanced features. Existing benchmarks primarily assess basic coding skills, while overlooking advanced Object-Oriented Programming (OOP) features (i.e., encapsulation, inheritance, and polymorphism). To fill these gaps, we propose JavaBench, a project-level Java benchmark that exercises OOP features. It comprises four Java projects with 389 methods in 106 Java classes. The test coverage is up to 92%, and JavaBench is attested by 282 undergraduate students, reaching a 90.93/100 average score (i.e., pass rate against the test suite), ensuring the quality of documentation, code skeleton, and tests. To better evaluate LLM's capability against JavaBench, we introduce a systematic evaluation design covering three context settings and five synthesis strategies at two granularities using three hierarchical metrics. Our extensive experiment yields several interesting findings. First, we noticed that regarding project-level Java programming, LLMs are far behind undergraduate students (no project can be correctly completed by any studied LLMs, and at most 41.17% Pass@5 in a more relaxed evaluation). Second, using method signature as prompt context may strike an ideal balance for project-level code generation. JavaBench is publicly available at https://github.com/java-bench/JavaBench.

Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning in capturing non-linear patterns of traffic data. However, the promising results achieved on current public datasets may not be applicable to practical scenarios due to limitations within these datasets. First, the limited sizes of them may not reflect the real-world scale of traffic networks. Second, the temporal coverage of these datasets is typically short, posing hurdles in studying long-term patterns and acquiring sufficient samples for training deep models. Third, these datasets often lack adequate metadata for sensors, which compromises the reliability and interpretability of the data. To mitigate these limitations, we introduce the LargeST benchmark dataset. It encompasses a total number of 8,600 sensors in California with a 5-year time coverage and includes comprehensive metadata. Using LargeST, we perform in-depth data analysis to extract data insights, benchmark well-known baselines in terms of their performance and efficiency, and identify challenges as well as opportunities for future research. We release the datasets and baseline implementations at: https://github.com/liuxu77/LargeST.

Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval. However, existing scene graph parsers that convert image captions into scene graphs often suffer from two types of errors. First, the generated scene graphs fail to capture the true semantics of the captions or the corresponding images, resulting in a lack of faithfulness. Second, the generated scene graphs have high inconsistency, with the same semantics represented by different annotations. To address these challenges, we propose a novel dataset, which involves re-annotating the captions in Visual Genome (VG) using a new intermediate representation called FACTUAL-MR. FACTUAL-MR can be directly converted into faithful and consistent scene graph annotations. Our experimental results clearly demonstrate that the parser trained on our dataset outperforms existing approaches in terms of faithfulness and consistency. This improvement leads to a significant performance boost in both image caption evaluation and zero-shot image retrieval tasks. Furthermore, we introduce a novel metric for measuring scene graph similarity, which, when combined with the improved scene graph parser, achieves state-of-the-art (SOTA) results on multiple benchmark datasets for the aforementioned tasks. The code and dataset are available at https://github.com/zhuang-li/FACTUAL .

Scientific reasoning relies not only on logical inference but also on activating prior knowledge and experiential structures. Memory can efficiently reuse knowledge and enhance reasoning consistency and stability. However, existing benchmarks mainly evaluate final answers or step-by-step coherence, overlooking the memory-driven mechanisms that underlie human reasoning, which involves activating anchors and attractors, then integrating them into multi-step inference. To address this gap, we propose A^3-Bench~ https://a3-bench.github.io, a benchmark designed to evaluate scientific reasoning through dual-scale memory-driven activation, grounded in Anchor and Attractor Activation. First, we annotate 2,198 science reasoning problems across domains using the SAPM process(subject, anchor & attractor, problem, and memory developing). Second, we introduce a dual-scale memory evaluation framework utilizing anchors and attractors, along with the AAUI(Anchor--Attractor Utilization Index) metric to measure memory activation rates. Finally, through experiments with various base models and paradigms, we validate A^3-Bench and analyze how memory activation impacts reasoning performance, providing insights into memory-driven scientific reasoning.

Multimodal large language models can write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue for 3D generation powered by their priors, world knowledge and reasoning. Yet existing benchmarks rarely evaluate 3D modeling through code. Such modeling demands more than runnable code: from a text or visual specification, a model must generate a parametric 3D program that is geometrically precise, semantically aligned and assembly-consistent. We introduce P3D-Bench, a benchmark for parametric 3D generation. Unlike a 3D mesh, a parametric 3D program exposes explicit dimensions, construction operations and part relations, revealing whether a model recovers a design's structure, not just its appearance. Under a unified protocol, P3D-Bench covers three task families (Text-to-3D, Image-to-3D and Assembly-3D) and scores each output for executability, geometric fidelity, topology, text-grounded constraints, multiview semantic alignment and part-level structure. We evaluate frontier MLLMs and text-only LLMs on 400 text cases, 400 image cases and 203 annotated assemblies, with domain-specific models as reference points. Our extensive evaluation yields three findings. First, assemblies are the hardest setting, where models still fail to compose multiple parts into a coherent structure. Second, models can often recover the global shape and semantic identity of the target object, yet fail to reproduce the precise parametric geometry specified by the input. Third, part-level modeling remains weak on assemblies, where models recover neither the geometry of each part nor the right number of parts. These results position P3D-Bench as a benchmark for evaluating precise parametric geometry and part-level structure in parametric 3D generation.

Remote sensing composed image retrieval (RSCIR) enables search in large satellite image archives using composed queries that combine a reference image with a textual modifier. Although RSCIR offers a flexible interface for expressing targeted retrieval intent, the transferability of modern composition methods to Earth observation (EO) imagery and their relevance to operational EO workflows remain underexplored. We address this gap through a unified benchmark and an application-oriented study. First, we systematically adapt and evaluate representative composed image retrieval methods with six vision-language backbones on PatternCom under a standardized protocol, analyzing their behavior across backbones, composition strategies, and query types. Second, we introduce xView2-CIR, a change-centric dataset for disaster and damage monitoring, where retrieval is conditioned on scene identity and a target post-event state. Our results show that training-free composition methods provide strong and scalable baselines for EO retrieval, while change-centric retrieval presents different challenges from attribute-based retrieval, particularly due to the need to preserve scene identity. Overall, this study establishes a practical benchmark for RSCIR and positions composed retrieval as a complementary tool for remote sensing image retrieval, archive exploration, and change analysis. The dataset and code are available at https://github.com/billpsomas/rscir.

Large language models (LLMs) offer an inexpensive yet powerful way to annotate text, but are often inconsistent when compared with experts. These errors can bias downstream estimates of population parameters such as regression coefficients and causal effects. To mitigate this bias, researchers have developed debiasing methods such as Design-based Supervised Learning (DSL) and Prediction-Powered Inference (PPI), which promise valid estimation by combining LLM annotations with a limited number of expensive expert annotations. Although these methods produce consistent estimates under theoretical assumptions, it is unknown how they compare in finite samples of sizes encountered in applied research. We make two contributions: First, we study how each method's performance scales with the number of expert annotations, highlighting regimes where LLM bias or limited expert labels significantly affect results. Second, we compare DSL and PPI across a range of tasks, finding that although both achieve low bias with large datasets, DSL often outperforms PPI on bias reduction and empirical efficiency, but its performance is less consistent across datasets. Our findings indicate that there is a bias-variance tradeoff at the level of debiasing methods, calling for more research on developing metrics for quantifying their efficiency in finite samples.

Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. By conducting a human evaluation on ten LLMs across different pretraining methods, prompts, and model scales, we make two important observations. First, we find instruction tuning, and not model size, is the key to the LLM's zero-shot summarization capability. Second, existing studies have been limited by low-quality references, leading to underestimates of human performance and lower few-shot and finetuning performance. To better evaluate LLMs, we perform human evaluation over high-quality summaries we collect from freelance writers. Despite major stylistic differences such as the amount of paraphrasing, we find that LMM summaries are judged to be on par with human written summaries.

Few-shot medical image segmentation (FS-MIS) aims to segment novel regions of interest (ROIs) from a few annotated support examples. Despite rapid progress, existing FS-MIS solutions span diverse paradigms but are evaluated under inconsistent settings, leaving their relative effectiveness unclear. We introduce FAME, a unified benchmark for evaluating FS-MIS solutions, covering specialists, SAM-based methods, CLIP-based methods, and MLLM-based methods. FAME contains 14,958 test samples across 7 anatomical sites, 9 imaging modalities, and 14 ROI categories, and evaluates models under zero-shot and ten-shot settings with additional assessment of target-absence recognition and generalization under covariate and semantic shifts. Our evaluation reveals several findings. First, effective few-shot segmentation depends on how models exploit support examples: direct visual adaptation generally outperforms prompt-based strategies. Second, increasing support examples improves performance only when models can effectively utilize them. Third, semantic transfer remains substantially more challenging than imaging-domain adaptation, and strong localization ability does not necessarily imply reliable target-absence recognition. We hope FAME provides a comprehensive understanding of current FS-MIS solutions and facilitates the development of more effective and reliable few-shot medical segmentation methods.

Solving partial differential equations (PDEs) with machine learning has recently attracted great attention, as PDEs are fundamental tools for modeling real-world systems that range from fundamental physical science to advanced engineering disciplines. Most real-world physical systems across various disciplines are actually involved in multiple coupled physical fields rather than a single field. However, previous machine learning studies mainly focused on solving single-field problems, but overlooked the importance and characteristics of multiphysics problems in real world. Multiphysics PDEs typically entail multiple strongly coupled variables, thereby introducing additional complexity and challenges, such as inter-field coupling. Both benchmarking and solving multiphysics problems with machine learning remain largely unexamined. To identify and address the emerging challenges in multiphysics problems, we mainly made three contributions in this work. First, we collect the first general multiphysics dataset, the Multiphysics Bench, that focuses on multiphysics PDE solving with machine learning. Multiphysics Bench is also the most comprehensive PDE dataset to date, featuring the broadest range of coupling types, the greatest diversity of PDE formulations, and the largest dataset scale. Second, we conduct the first systematic investigation on multiple representative learning-based PDE solvers, such as PINNs, FNO, DeepONet, and DiffusionPDE solvers, on multiphysics problems. Unfortunately, naively applying these existing solvers usually show very poor performance for solving multiphysics. Third, through extensive experiments and discussions, we report multiple insights and a bag of useful tricks for solving multiphysics with machine learning, motivating future directions in the study and simulation of complex, coupled physical systems.

Large language models (LLMs) based agent systems have made great strides in real-world applications beyond traditional NLP tasks. This paper proposes a new LLM-powered Multi-Agent System (LLM-MAS) benchmark, Collab-Overcooked, built on the popular Overcooked-AI game with more applicable and challenging tasks in interactive environments. Collab-Overcooked extends existing benchmarks from two novel perspectives. First, it provides a multi-agent framework supporting diverse tasks and objectives and encourages collaboration through natural language communication. Second, it introduces a spectrum of process-oriented evaluation metrics to assess the fine-grained collaboration capabilities of different LLM agents, a dimension often overlooked in prior work. We conduct extensive experiments over 10 popular LLMs and show that, while the LLMs present a strong ability in goal interpretation, there is a significant discrepancy in active collaboration and continuous adaption that are critical for efficiently fulfilling complicated tasks. Notably, we highlight the strengths and weaknesses in LLM-MAS and provide insights for improving and evaluating LLM-MAS on a unified and open-sourced benchmark. Environments, 30 open-ended tasks, and an integrated evaluation package are now publicly available at https://github.com/YusaeMeow/Collab-Overcooked.

As the number of novel data-driven approaches to material science continues to grow, it is crucial to perform consistent quality, reliability and applicability assessments of model performance. In this paper, we benchmark the Materials Optimal Descriptor Network (MODNet) method and architecture against the recently released MatBench v0.1, a curated test suite of materials datasets. MODNet is shown to outperform current leaders on 6 of the 13 tasks, whilst closely matching the current leaders on a further 2 tasks; MODNet performs particularly well when the number of samples is below 10,000. Attention is paid to two topics of concern when benchmarking models. First, we encourage the reporting of a more diverse set of metrics as it leads to a more comprehensive and holistic comparison of model performance. Second, an equally important task is the uncertainty assessment of a model towards a target domain. Significant variations in validation errors can be observed, depending on the imbalance and bias in the training set (i.e., similarity between training and application space). By using an ensemble MODNet model, confidence intervals can be built and the uncertainty on individual predictions can be quantified. Imbalance and bias issues are often overlooked, and yet are important for successful real-world applications of machine learning in materials science and condensed matter.

Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process is essential to reducing labor-intensive efforts for data scientists and enabling scalable data-driven applications. Recently, large language model (LLM)-based data agents have emerged as a promising solution to automate data science workflows. However, the field lacks comprehensive benchmarks to rigorously evaluate these agents across diverse scenarios with fine-grained granularity. To address this gap, we propose AgenticDataBench, a comprehensive benchmark featuring realistic tasks spanning diverse domains with fine-grained ground-truth labels. This enables evaluations to capture the diversity and complexity of data science workflows and the detailed performance of agents. First, to cover diverse domains, we collect real datasets and tasks from 15 vertical domains, including 5 real-world B2B use cases from a leading fintech company. Second, to remove redundancy in real-world tasks and generate high-quality tasks for domains lacking real data, we introduce data science skills, recurring data-centric operational patterns, and quantify benchmark coverage by the number of skills included. Representative skills are extracted from large-scale task solutions on Stack Overflow using skill-aligned hierarchical clustering. Third, for real-world business tasks, we select task-solution pairs that maximize diversity in skill composition, ensuring broad coverage of practical scenarios. Fourth, to generate realistic tasks for devise domains without real tasks, we propose a systematic LLM-based task generation approach to create workflows and tasks based on these skills. Finally, we evaluate state-of-the-art data agents using our annotated benchmark and open-sourced testbed, providing detailed skill-level insights.

Many recent works have explored using language models for planning problems. One line of research focuses on translating natural language descriptions of planning tasks into structured planning languages, such as the planning domain definition language (PDDL). While this approach is promising, accurately measuring the quality of generated PDDL code continues to pose significant challenges. First, generated PDDL code is typically evaluated using planning validators that check whether the problem can be solved with a planner. This method is insufficient because a language model might generate valid PDDL code that does not align with the natural language description of the task. Second, existing evaluation sets often have natural language descriptions of the planning task that closely resemble the ground truth PDDL, reducing the challenge of the task. To bridge this gap, we introduce \benchmarkName, a benchmark designed to evaluate language models' ability to generate PDDL code from natural language descriptions of planning tasks. We begin by creating a PDDL equivalence algorithm that rigorously evaluates the correctness of PDDL code generated by language models by flexibly comparing it against a ground truth PDDL. Then, we present a dataset of 132,037 text-to-PDDL pairs across 13 different tasks, with varying levels of difficulty. Finally, we evaluate several API-access and open-weight language models that reveal this task's complexity. For example, 87.6% of the PDDL problem descriptions generated by GPT-4o are syntactically parseable, 82.2% are valid, solve-able problems, but only 35.1% are semantically correct, highlighting the need for a more rigorous benchmark for this problem.

Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. Moreover, current datasets may not effectively diagnose these methods. To address these challenges, we first introduce a novel dataset, FortisAVQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-AVQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic Network (MAVEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisAVQA, with a notable improvement of 7.81\%. Extensive ablation studies on both datasets validate the effectiveness of our debiasing components. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. Our dataset and code are available at https://github.com/reml-group/fortisavqa.

Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many reference patches produce close-to-zero runtime changes. Second, we show that public submission rankings depend strongly on the benchmark scoring rule. Among eight public submissions shared by GSO and SWE-fficiency, the official rankings disagree on 9 of 28 pairwise submission comparisons, and SWE-fficiency's leaderboard scoring rule assigns the worst ten tasks overly high score weights of 58.5%-82.8%. Third, looking across 10 public submissions for each task, we find that at least one submission matches or beats the reference patch on 85.3% (384/450) of replay-valid GSO and SWE-fficiency tasks, and beats the unoptimized base code on 99.8% (449/450). Our study complements leaderboard scores by identifying tasks with more reliable performance signals, quantifying per-task score contributions, and exposing the remaining performance gaps that are hidden by aggregate rankings.

The GitHub issue resolution task aims to resolve issues reported in repositories automatically. With advances in large language models (LLMs), this task has gained increasing attention, and several benchmarks are proposed to evaluate the issue resolution ability of LLMs. However, existing benchmarks have three main limitations. First, current benchmarks focus on a single programming language, limiting the evaluation of issues from repositories across different languages. Second, they usually cover a narrow range of domains, which may fail to represent the diversity of real-world issues. Third, existing benchmarks rely solely on textual information in issue descriptions, overlooking multimodal information such as images in issues. In this paper, we propose OmniGIRL, a GitHub Issue ResoLution benchmark that is multilingual, multimodal, and multi-domain. OmniGIRL includes 959 task instances, which are collected from repositories across four programming languages (i.e., Python, JavaScript, TypeScript, and Java) and eight different domains. Our evaluation shows that current LLMs show limited performances on OmniGIRL. Notably, the best-performing model, GPT-4o, resolves only 8.6% of the issues. Besides, we find that current LLMs struggle to resolve issues requiring understanding images. The best performance is achieved by Claude-3.5-Sonnet, which resolves only 10.5% of the issues with image information. Finally, we analyze the reasons behind current LLMs' failure on OmniGIRL, providing insights for future improvements.

The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid performance saturation and a lack of true generalization testing. Existing benchmarks often exhibit significant domain overlap between training and evaluation, trivializing success rates and obscuring insights into robustness. We introduce RoboLab, a simulation benchmarking framework designed to address these challenges. Concretely, our framework is designed to answer two questions: (1) to what extent can we understand the performance of a real-world policy by analyzing its behavior in simulation, and (2) which external factors most strongly affect that behavior under controlled perturbations. First, RoboLab enables human-authored and LLM-enabled generation of scenes and tasks in a robot- and policy-agnostic manner within a physically realistic and photorealistic simulation. With this, we propose the RoboLab-120 benchmark, consisting of 120 tasks categorized into three competency axes: visual, procedural, relational competency, across three difficulty levels. Second, we introduce a systematic analysis of real-world policies that quantify both their performance and the sensitivity of their behavior to controlled perturbations, indicating that high-fidelity simulation can serve as a proxy for analyzing performance and its dependence on external factors. Evaluation with RoboLab exposes significant performance gap in current state-of-the-art models. By providing granular metrics and a scalable toolset, RoboLab offers a scalable framework for evaluating the true generalization capabilities of task-generalist robotic policies.

LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBench-X, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency across 176 tasks in 15 categories. Our systematic comparison of five representative methods yields three main findings. First, task structure determines correctness more than method design. Category explains nearly three times more variance in semantic correctness than method (9.4% vs 3.3% explained deviance), and 72% of Fusion tasks fail across all five methods while Math tasks are solved consistently. Second, iterative refinement improves correctness, but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from 1.58times to 1.44times; newly rescued kernels consistently underperform persistently correct ones (1.16times vs 1.58times speedup in round~0to1). Third, correctness does not imply efficiency. 46.6% of correct kernels are slower than the PyTorch eager baseline, and cross-hardware speedup variance reaches 21.4times. Besides, quantization remains completely unsolved (0/30 successes) despite non-trivial compilation rates, revealing systematic misunderstanding of numerical computation contracts rather than surface-level syntax errors. These findings suggest that future progress depends on handling global coordination, explicitly modeling numerical precision, and incorporating hardware efficiency into generation. The code is available at https://github.com/BonnieW05/KernelBenchX

Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than the professional Cinematic Language criteria by which films are actually made and judged, so they assess basic video plausibility rather than film-grade craft. We introduce FilmBench, a text-to-video (T2V) and reference-to-video (R2V) benchmark grounded in the professional Cinematic Language of the film- academy tradition and co-developed with directors and faculty from the Beijing Film Academy and the Hujing Digital Media & Entertainment Group film studio. It rests on three choices. First, prompts are reverse-engineered from clips of award-winning films spanning 20 cinematic genres and chosen by professional directors, so every prompt is anchored to a verified live-action reference; the prompts follow real shot lists, and most script multiple shots (1,056 of the 1,169 prompts are multi-shot), unlike prior single-clip benchmarks. Second, evaluation follows a three-level Cinematic taxonomy of 3 axes, 12 components and 35 (T2V) +3 (R2V-only) sub-metrics. Third, we develop an in-house expert-grade automatic evaluation agent and open-source its core suite of Cinematic Language operators (FilmOps). Benchmarking leading video generation models (9 for T2V, 7 for R2V), the evaluator reproduces the human model ranking at model-level Spearman ho = 0.95 (T2V) and 0.96 (R2V). Scores fall well below prior web-style benchmarks, with two consistent gaps in dynamic aesthetics and a marked single- to multi-shot performance drop that widens for weaker models.

To improve the prognosis of patients suffering from pulmonary diseases, such as lung cancer, early diagnosis and treatment are crucial. The analysis of CT images is invaluable for diagnosis, whereas high quality segmentation of the airway tree are required for intervention planning and live guidance during bronchoscopy. Recently, the Multi-domain Airway Tree Modeling (ATM'22) challenge released a large dataset, both enabling training of deep-learning based models and bringing substantial improvement of the state-of-the-art for the airway segmentation task. However, the ATM'22 dataset includes few patients with severe pathologies affecting the airway tree anatomy. In this study, we introduce a new public benchmark dataset (AeroPath), consisting of 27 CT images from patients with pathologies ranging from emphysema to large tumors, with corresponding trachea and bronchi annotations. Second, we present a multiscale fusion design for automatic airway segmentation. Models were trained on the ATM'22 dataset, tested on the AeroPath dataset, and further evaluated against competitive open-source methods. The same performance metrics as used in the ATM'22 challenge were used to benchmark the different considered approaches. Lastly, an open web application is developed, to easily test the proposed model on new data. The results demonstrated that our proposed architecture predicted topologically correct segmentations for all the patients included in the AeroPath dataset. The proposed method is robust and able to handle various anomalies, down to at least the fifth airway generation. In addition, the AeroPath dataset, featuring patients with challenging pathologies, will contribute to development of new state-of-the-art methods. The AeroPath dataset and the web application are made openly available.

We introduce TimeSeriesGym, a scalable benchmarking framework for evaluating Artificial Intelligence (AI) agents on time series machine learning engineering challenges. Existing benchmarks lack scalability, focus narrowly on model building in well-defined settings, and evaluate only a limited set of research artifacts (e.g., CSV submission files). To make AI agent benchmarking more relevant to the practice of machine learning engineering, our framework scales along two critical dimensions. First, recognizing that effective ML engineering requires a range of diverse skills, TimeSeriesGym incorporates challenges from diverse sources spanning multiple domains and tasks. We design challenges to evaluate both isolated capabilities (including data handling, understanding research repositories, and code translation) and their combinations, and rather than addressing each challenge independently, we develop tools that support designing multiple challenges at scale. Second, we implement evaluation mechanisms for multiple research artifacts, including submission files, code, and models, using both precise numeric measures and more flexible LLM-based evaluation approaches. This dual strategy balances objective assessment with contextual judgment. Although our initial focus is on time series applications, our framework can be readily extended to other data modalities, broadly enhancing the comprehensiveness and practical utility of agentic AI evaluation. We open-source our benchmarking framework to facilitate future research on the ML engineering capabilities of AI agents.

While the general machine learning (ML) community has benefited from public datasets, tasks, and models, the progress of ML in healthcare has been hampered by a lack of such shared assets. The success of foundation models creates new challenges for healthcare ML by requiring access to shared pretrained models to validate performance benefits. We help address these challenges through three contributions. First, we publish a new dataset, EHRSHOT, which contains deidentified structured data from the electronic health records (EHRs) of 6,739 patients from Stanford Medicine. Unlike MIMIC-III/IV and other popular EHR datasets, EHRSHOT is longitudinal and not restricted to ICU/ED patients. Second, we publish the weights of CLMBR-T-base, a 141M parameter clinical foundation model pretrained on the structured EHR data of 2.57M patients. We are one of the first to fully release such a model for coded EHR data; in contrast, most prior models released for clinical data (e.g. GatorTron, ClinicalBERT) only work with unstructured text and cannot process the rich, structured data within an EHR. We provide an end-to-end pipeline for the community to validate and build upon its performance. Third, we define 15 few-shot clinical prediction tasks, enabling evaluation of foundation models on benefits such as sample efficiency and task adaptation. Our model and dataset are available via a research data use agreement from the Stanford AIMI Center. Code to reproduce our results are available at our Github repo: https://github.com/som-shahlab/ehrshot-benchmark

We introduce WebApp1K, a practical code-generation benchmark to measure LLM ability to develop web apps. This benchmark aims to calibrate LLM output and aid the models to progressively improve code correctness and functionality. The benchmark is lightweight and easy to run. We present the initial version of WebApp1K, and share our findings of running the benchmark against the latest frontier LLMs. First, open source LLMs deliver impressive performance, closely trailing behind GPT-4o and Claude 3.5. Second, model size has strong correlation with code correctness. Third, no prompting techniques have been found to lift performance either universally to all models, or significantly to a single model.

In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first class-level code generation benchmark ClassEval of 100 class-level Python code generation tasks with approximately 500 person-hours. Based on it, we then perform the first study of 11 state-of-the-art LLMs on class-level code generation. Based on our results, we have the following main findings. First, we find that all existing LLMs show much worse performance on class-level code generation compared to on standalone method-level code generation benchmarks like HumanEval; and the method-level coding ability cannot equivalently reflect the class-level coding ability among LLMs. Second, we find that GPT-4 and GPT-3.5 still exhibit dominate superior than other LLMs on class-level code generation, and the second-tier models includes Instruct-Starcoder, Instruct-Codegen, and Wizardcoder with very similar performance. Third, we find that generating the entire class all at once (i.e. holistic generation strategy) is the best generation strategy only for GPT-4 and GPT-3.5, while method-by-method generation (i.e. incremental and compositional) is better strategies for the other models with limited ability of understanding long instructions and utilizing the middle information. Lastly, we find the limited model ability of generating method-dependent code and discuss the frequent error types in generated classes. Our benchmark is available at https://github.com/FudanSELab/ClassEval.

The explosive growth in academic literature necessitates automated deep research (DR) agents, yet their evaluation remains a significant challenge. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and reasoning. Second, existing benchmarks favor general domains over the scientific domains that are the core application for DR agents. To address these gaps, we introduce Dr.Mi-Bench, a Modular-integrated benchmark for scientific DR agents. Grounded in academic literature, our benchmark uses a human-annotated dataset of 200 instances across 10 scientific domains, including both research and review papers. Besides, we also propose a Modular-integrated Evaluation Paradigm for DR Agents (Dr.Mi-Eval), a novel modular-integrated evaluation paradigm, which leverages the rich structure of academic papers to assess the core competencies of planning, retrieval, and reasoning through two complementary modes: an end-to-end evaluation for DR agents and an isolated evaluation for foundational LLMs as potential backbones. Experimental results reveal a fragmented performance landscape: agents exhibit specialized strengths but share critical weaknesses, most notably in performing the multi-source retrieval required for review-style tasks and performing consistently across diverse scientific fields. Moreover, improving high-level planning capability is the crucial factor for unlocking the reasoning potential of foundational LLMs as backbones. By exposing these actionable failure modes, Dr.Mi-Bench provides a diagnostic tool to guide the development of more reliable academic research assistants.

As web agents increasingly demonstrate capabilities in automated task execution, the development of robust evaluation frameworks for assessing their navigation and task completion performance has emerged as a critical research priority. However, existing benchmarks exhibit fundamental limitations. First, they suffer from insufficient scale and limited domain diversity, constraining comprehensive evaluation of cross-domain generalization. Second, prevailing LLM-as-Judge evaluation methodologies inadequately capture fine-grained interaction semantics, particularly regarding precise query formulation and filtering operations. Third, current benchmarks predominantly emphasize navigation success metrics while neglecting critical requirements for real-world deployment scenarios. To address these limitations, we introduce WebRetriever, a large-scale benchmark encompassing 800 websites and 1,550 tasks across diverse domains, including consumer, professional, and enterprise sectors, with comprehensive coverage of user intent patterns. We propose NavEval (Navigation Evaluation), a novel LLM-as-Judge framework that leverages rich interaction context beyond visual screenshots, achieving state-of-the-art alignment with human judgment across multiple evaluation datasets. Furthermore, we establish three complementary evaluation protocols that collectively provide holistic assessment of web agent capabilities: navigation proficiency, knowledge-assisted interaction, and end-to-end task completion with information extraction. Extensive experimental analysis reveals substantial performance disparities across evaluation protocols, demonstrating that navigation success alone is an insufficient predictor of real-world application effectiveness. WebRetriever delivers fine-grained diagnostic insights into agent capabilities and establishes a rigorous foundation for advancing web agent research and development.

While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing benchmarks suffer from three critical limitations: a pronounced bias towards high-resource languages, a focus on low-level recognition (ASR) rather than semantic reasoning, and a neglect of regional dialects. To bridge this gap, we introduce PolySpeech-100, a massive-scale benchmark designed to assess `native-level' speech comprehension across 110 linguistic variants. We employ a novel hybrid construction pipeline that augments gold-standard human recordings with instruction-driven synthetic speech, allowing us to cover 19 distinct Chinese dialects and over 80 low-resource languages. Extensive evaluation of 22 state-of-the-art models (including Gemini-3, GPT-Audio, and Qwen2.5-Omni) yields pivotal insights. First, we demonstrate that open-source E2E models outperform Cascade (ASR+LLM) systems on heavy dialects, proving that direct audio processing preserves critical paralinguistic cues and prosodic features (e.g., intonation, stress) that are often lost in standard transcription. Second, we reveal a significant performance gap: while commercial models maintain robustness, open-source models suffer catastrophic degradation on low-resource languages. Finally, counter-intuitively, we observe that under standard zero-shot settings, Chain-of-Thought prompting frequently degrades speech understanding performance for most evaluated models, revealing a potential modality alignment gap in current architectures. PolySpeech-100 establishes a rigorous standard for the next generation of inclusive, omni-capable Speech-LLMs. The data, demo, and code are publicly available at https://github.com/YoungSeng/PolySpeech-100.

We formalize and enable the task of open tree decomposition, which segments an image into hierarchical trees of visual components with unconstrained granularity and flexibility. Specifically, we provide the foundation benchmark for this new paradigm with the following three key contributions. First, we overcome the prohibitively high cognitive and physical bottlenecks of manual annotation by developing a fully automated generation pipeline that synergizes the semantic reasoning of Large Vision-Language Models (LVLMs) with the precise geometric grounding of SAM 3. Second, leveraging this pipeline, we construct COCOTree, a massive-scale benchmark featuring over 21K images and 1.8M structural nodes. By embracing an open-vocabulary space of over 3.5K unique labels, it successfully captures the long-tail distribution of complex physical assemblies. Notably, rigorous human evaluation confirms our generated annotations demonstrate strong alignment with human structural judgment. Third, we establish a standardized evaluation protocol by proposing the Open Tree Quality (OTQ) metric, which jointly assesses mask precision, label accuracy, and structural consistency. We release our dataset and benchmark code at https://github.com/melonkick3090/COCOTree.

The evaluation of generated reports remains a critical challenge in Computed Tomography (CT) report generation, due to the large volume of text, the diversity and complexity of findings, and the presence of fine-grained, disease-oriented attributes. Conventional evaluation metrics offer only coarse measures of lexical overlap or entity matching and fail to reflect the granular diagnostic accuracy required for clinical use. To address this gap, we propose CT-FineBench, a benchmark built from CT-RATE and Merlin to evaluate the fine-grained factual consistency of CT reports, constructed from CT-RATE and Merlin. Our benchmark is constructed through a meticulous, Question-Answering (QA) based process: first, we identify and structure key, finding-specific clinical attributes (like location, size, margin). Second, we systematically transform these attributes into a QA dataset, where questions probe for specific clinical details grounded in gold-standard reports. The evaluation protocol for CT-FineBench involves using this QA dataset to query a machine-generated report and scoring the correctness of the answers. This allows for a comprehensive, interpretable, and clinically-relevant assessment, moving beyond superficial lexical overlap to pinpoint specific clinical errors. Experiments show that CT-FineBench correlates better with expert clinical assessment and is substantially more sensitive to fine-grained factual errors than prior metrics.

Facial expression image editing requires fine-grained control to strictly preserve human identity and background while precisely manipulating expression. However, existing editing benchmarks primarily focus on general scenarios, lacking high-quality facial images and corresponding editing instructions. Furthermore, current evaluation metrics exhibit systemic biases in this task, often favoring lazy editing or overfit editing. To bridge these gaps, we propose FED-Bench, a comprehensive benchmark featuring rigorous testing and an accurate evaluation suite. First, we carefully construct a benchmark of 747 triplets through a cascaded and scalable pipeline, each comprising an original image, an editing instruction, and a ground-truth image for precise evaluation. Second, we introduce FED-Score, a cross-granularity evaluation protocol that disentangles assessment into three dimensions: Alignment for verifying instruction following, Fidelity for testing image quality and identity preservation, and Relative Expression Gain for quantifying the magnitude of expression changes, effectively mitigating the aforementioned evaluation biases. Third, we benchmark 18 image editing models, revealing that current approaches struggle to simultaneously achieve high fidelity and accurate expression manipulation, with fine-grained instruction following identified as the primary bottleneck. Finally, leveraging the scalable characteristic of introduced benchmark engine, we provide a 20k+ in-the-wild facial training set and demonstrate its effectiveness by fine-tuning a baseline model that achieves significant performance gains. Our benchmark and related code will be made publicly open soon.

Deep learning models often inherit biases from their training data. While fairness across gender and ethnicity is well-studied, fine-grained skin tone analysis remains a challenge due to the lack of granular, annotated datasets. Existing methods often rely on the medical 6-tone Fitzpatrick scale, which lacks visual representativeness, or use small, private datasets that prevent reproducibility, or often rely on classic computer vision pipelines, with a few using deep learning. They overlook issues like train-test leakage and dataset imbalance, and are limited by small or unavailable datasets. In this work, we present a comprehensive framework for skin tone fairness. First, we introduce the STW, a large-scale, open-access dataset comprising 42,313 images from 3,564 individuals, labeled using the 10-tone MST scale. Second, we benchmark both Classic Computer Vision (SkinToneCCV) and Deep Learning approaches, demonstrating that classic models provide near-random results, while deep learning reaches nearly annotator accuracy. Finally, we propose SkinToneNet, a fine-tuned ViT that achieves state-of-the-art generalization on out-of-domain data, which enables reliable fairness auditing of public datasets like CelebA and VGGFace2. This work provides state-of-the-art results in skin tone classification and fairness assessment. Code and data available soon

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and over time. However, traditional classifiers, confined to fixed categories, require frequent retraining when new policies are introduced. Vision-language models (VLMs) offer a more adaptable and generalizable foundation for dynamic safety guardrails. Despite this potential, existing VLM-based safeguarding methods are typically trained and evaluated under only a fixed safety policy. We find that these models are heavily overfitted to the seen policy, fail to generalize to unseen policies, and even lose the basic instruction-following ability and general knowledge. To address this issue, in this paper we make two key contributions. First, we benchmark the cross-policy generalization performance of existing VLMs with SafeEditBench, a new evaluation suite. SafeEditBench leverages image-editing models to convert unsafe images into safe counterparts, producing policy-aligned datasets where each safe-unsafe image pair remains visually similar except for localized regions violating specific safety rules. Human annotators then provide accurate safe/unsafe labels under five distinct policies, enabling fine-grained assessment of policy-aware generalization. Second, we introduce SafeGuard-VL, a reinforcement learning-based method with verifiable rewards (RLVR) for robust unsafe-image guardrails. Instead of relying solely on supervised fine-tuning (SFT) under fixed policies, SafeGuard-VL explicitly optimizes the model with policy-grounded rewards, promoting verifiable adaptation across evolving policies. Extensive experiments verify the effectiveness of our method for unsafe image guardrails across various policies.

We introduce FinCriticalED (Financial Critical Error Detection), a visual benchmark for evaluating OCR and vision language models on financial documents at the fact level. Financial documents contain visually dense and table heavy layouts where numerical and temporal information is tightly coupled with structure. In high stakes settings, small OCR mistakes such as sign inversion or shifted dates can lead to materially different interpretations, while traditional OCR metrics like ROUGE and edit distance capture only surface level text similarity. \ficriticaled provides 500 image-HTML pairs with expert annotated financial facts covering over seven hundred numerical and temporal facts. It introduces three key contributions. First, it establishes the first fact level evaluation benchmark for financial document understanding, shifting evaluation from lexical overlap to domain critical factual correctness. Second, all annotations are created and verified by financial experts with strict quality control over signs, magnitudes, and temporal expressions. Third, we develop an LLM-as-Judge evaluation pipeline that performs structured fact extraction and contextual verification for visually complex financial documents. We benchmark OCR systems, open source vision language models, and proprietary models on FinCriticalED. Results show that although the strongest proprietary models achieve the highest factual accuracy, substantial errors remain in visually intricate numerical and temporal contexts. Through quantitative evaluation and expert case studies, FinCriticalED provides a rigorous foundation for advancing visual factual precision in financial and other precision critical domains.

As large language models (LLMs) are increasingly used in legal applications, current evaluation benchmarks tend to focus mainly on factual accuracy while largely neglecting important linguistic quality aspects such as clarity, coherence, and terminology. To address this gap, we propose three steps: First, we develop a regression model to evaluate the quality of legal texts based on clarity, coherence, and terminology. Second, we create a specialized set of legal questions. Third, we analyze 49 LLMs using this evaluation framework. Our analysis identifies three key findings: First, model quality levels off at 14 billion parameters, with only a marginal improvement of 2.7% noted at 72 billion parameters. Second, engineering choices such as quantization and context length have a negligible impact, as indicated by statistical significance thresholds above 0.016. Third, reasoning models consistently outperform base architectures. A significant outcome of our research is the release of a ranking list and Pareto analysis, which highlight the Qwen3 series as the optimal choice for cost-performance tradeoffs. This work not only establishes standardized evaluation protocols for legal LLMs but also uncovers fundamental limitations in current training data refinement approaches. Code and models are available at: https://github.com/lyxx3rd/LegalEval-Q.

While recent research increasingly emphasizes the value of human-LLM collaboration in competitive programming and proposes numerous empirical methods, a comprehensive understanding remains elusive due to the fragmented nature of existing studies and their use of diverse, application-specific human feedback. Thus, our work serves a three-fold purpose: First, we present the first taxonomy of human feedback consolidating the entire programming process, which promotes fine-grained evaluation. Second, we introduce ELABORATIONSET, a novel programming dataset specifically designed for human-LLM collaboration, meticulously annotated to enable large-scale simulated human feedback and facilitate costeffective real human interaction studies. Third, we introduce ELABORATION, a novel benchmark to facilitate a thorough assessment of human-LLM competitive programming. With ELABORATION, we pinpoint strengthes and weaknesses of existing methods, thereby setting the foundation for future improvement. Our code and dataset are available at https://github.com/SCUNLP/ELABORATION

The lack of standardized evaluation benchmarks in the medical domain for text inputs can be a barrier to widely adopting and leveraging the potential of natural language models for health-related downstream tasks. This paper revisited an openly available MIMIC-IV benchmark for electronic health records (EHRs) to address this issue. First, we integrate the MIMIC-IV data within the Hugging Face datasets library to allow an easy share and use of this collection. Second, we investigate the application of templates to convert EHR tabular data to text. Experiments using fine-tuned and zero-shot LLMs on the mortality of patients task show that fine-tuned text-based models are competitive against robust tabular classifiers. In contrast, zero-shot LLMs struggle to leverage EHR representations. This study underlines the potential of text-based approaches in the medical field and highlights areas for further improvement.

Retrieval augmented generation (RAG) holds great promise in addressing challenges associated with long video understanding. These methods retrieve useful moments from long videos for their presented tasks, thereby enabling multimodal large language models (MLLMs) to generate high-quality answers in a cost-effective way. In this work, we present MomentSeeker, a comprehensive benchmark to evaluate retrieval models' performance in handling general long-video moment retrieval (LVMR) tasks. MomentSeeker offers three key advantages. First, it incorporates long videos of over 500 seconds on average, making it the first benchmark specialized for long-video moment retrieval. Second, it covers a wide range of task categories (including Moment Search, Caption Alignment, Image-conditioned Moment Search, and Video-conditioned Moment Search) and diverse application scenarios (e.g., sports, movies, cartoons, and ego), making it a comprehensive tool for assessing retrieval models' general LVMR performance. Additionally, the evaluation tasks are carefully curated through human annotation, ensuring the reliability of assessment. We further fine-tune an MLLM-based LVMR retriever on synthetic data, which demonstrates strong performance on our benchmark. We perform extensive experiments with various popular multimodal retrievers based on our benchmark, whose results highlight the challenges of LVMR and limitations for existing methods. Our created resources will be shared with community to advance future research in this field.

Multimodal Large Language Models (MLLMs) have shown significant progress in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique challenges due to the need for real-time processing of continuous online video streams. To this end, this paper presents systematic efforts from three perspectives: evaluation benchmark, model architecture, and training strategy. First, we introduce OVBench, a comprehensive question-answering benchmark specifically designed to evaluate models' ability to perceive, memorize, and reason within online video contexts. It features six core task types across three temporal contexts-past, present, and future-forming 16 subtasks from diverse datasets. Second, we propose a new Pyramid Memory Bank (PMB) that effectively retains key spatiotemporal information in video streams. Third, we proposed an offline-to-online learning paradigm, designing an interleaved dialogue format for online video data and constructing an instruction-tuning dataset tailored for online video training. This framework led to the development of VideoChat-Online, a robust and efficient model for online video understanding. Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy.

High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks. However, as frontier tasks in robotics get more advanced, they require faster simulation speed, more intricate test environments, and larger demonstration datasets. To this end, we present MS-HAB, a holistic benchmark for low-level manipulation and in-home object rearrangement. First, we provide a GPU-accelerated implementation of the Home Assistant Benchmark (HAB). We support realistic low-level control and achieve over 3x the speed of previous magical grasp implementations at similar GPU memory usage. Second, we train extensive reinforcement learning (RL) and imitation learning (IL) baselines for future work to compare against. Finally, we develop a rule-based trajectory filtering system to sample specific demonstrations from our RL policies which match predefined criteria for robot behavior and safety. Combining demonstration filtering with our fast environments enables efficient, controlled data generation at scale.

Automatic speech Recognition (ASR) is a fundamental and important task in the field of speech and natural language processing. It is an inherent building block in many applications such as voice assistant, speech translation, etc. Despite the advancement of ASR technologies in recent years, it is still inevitable for modern ASR systems to have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc. Therefore, the error correction in ASR is crucial. Motivated by this, this paper studies ASR error correction in the Chinese language, which is one of the most popular languages and enjoys a large number of users in the world. We first create a benchmark dataset named ASR-EC that contains a wide spectrum of ASR errors generated by industry-grade ASR systems. To the best of our knowledge, it is the first Chinese ASR error correction benchmark. Then, inspired by the recent advances in large language models (LLMs), we investigate how to harness the power of LLMs to correct ASR errors. We apply LLMs to ASR error correction in three paradigms. The first paradigm is prompting, which is further categorized as zero-shot, few-shot, and multi-step. The second paradigm is finetuning, which finetunes LLMs with ASR error correction data. The third paradigm is multi-modal augmentation, which collectively utilizes the audio and ASR transcripts for error correction. Extensive experiments reveal that prompting is not effective for ASR error correction. Finetuning is effective only for a portion of LLMs. Multi-modal augmentation is the most effective method for error correction and achieves state-of-the-art performance.

Evaluations of Large Language Models (LLMs) on knowledge-intensive tasks and factual accuracy often focus on high-resource languages primarily because datasets for low-resource languages (LRLs) are scarce. In this paper, we present Uhura -- a new benchmark that focuses on two tasks in six typologically-diverse African languages, created via human translation of existing English benchmarks. The first dataset, Uhura-ARC-Easy, is composed of multiple-choice science questions. The second, Uhura-TruthfulQA, is a safety benchmark testing the truthfulness of models on topics including health, law, finance, and politics. We highlight the challenges creating benchmarks with highly technical content for LRLs and outline mitigation strategies. Our evaluation reveals a significant performance gap between proprietary models such as GPT-4o and o1-preview, and Claude models, and open-source models like Meta's LLaMA and Google's Gemma. Additionally, all models perform better in English than in African languages. These results indicate that LMs struggle with answering scientific questions and are more prone to generating false claims in low-resource African languages. Our findings underscore the necessity for continuous improvement of multilingual LM capabilities in LRL settings to ensure safe and reliable use in real-world contexts. We open-source the Uhura Benchmark and Uhura Platform to foster further research and development in NLP for LRLs.

Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on human-designed text prompts or fixed templates, limiting their diversity and complexity, and yielding low discriminative power. We propose ConceptMix, a scalable, controllable, and customizable benchmark which automatically evaluates compositional generation ability of T2I models. This is done in two stages. First, ConceptMix generates the text prompts: concretely, using categories of visual concepts (e.g., objects, colors, shapes, spatial relationships), it randomly samples an object and k-tuples of visual concepts, then uses GPT4-o to generate text prompts for image generation based on these sampled concepts. Second, ConceptMix evaluates the images generated in response to these prompts: concretely, it checks how many of the k concepts actually appeared in the image by generating one question per visual concept and using a strong VLM to answer them. Through administering ConceptMix to a diverse set of T2I models (proprietary as well as open ones) using increasing values of k, we show that our ConceptMix has higher discrimination power than earlier benchmarks. Specifically, ConceptMix reveals that the performance of several models, especially open models, drops dramatically with increased k. Importantly, it also provides insight into the lack of prompt diversity in widely-used training datasets. Additionally, we conduct extensive human studies to validate the design of ConceptMix and compare our automatic grading with human judgement. We hope it will guide future T2I model development.

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address. First, there is no clear standard of practice regarding jailbreaking evaluation. Second, existing works compute costs and success rates in incomparable ways. And third, numerous works are not reproducible, as they withhold adversarial prompts, involve closed-source code, or rely on evolving proprietary APIs. To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (2) a jailbreaking dataset comprising 100 behaviors -- both original and sourced from prior work -- which align with OpenAI's usage policies; (3) a standardized evaluation framework that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard that tracks the performance of attacks and defenses for various LLMs. We have carefully considered the potential ethical implications of releasing this benchmark, and believe that it will be a net positive for the community. Over time, we will expand and adapt the benchmark to reflect technical and methodological advances in the research community.

Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub). Our LVLM-eHub consists of 8 representative LVLMs such as InstructBLIP and MiniGPT-4, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The former evaluates 6 categories of multimodal capabilities of LVLMs such as visual question answering and embodied artificial intelligence on 47 standard text-related visual benchmarks, while the latter provides the user-level evaluation of LVLMs in an open-world question-answering scenario. The study reveals several innovative findings. First, instruction-tuned LVLM with massive in-domain data such as InstructBLIP heavily overfits many existing tasks, generalizing poorly in the open-world scenario. Second, instruction-tuned LVLM with moderate instruction-following data may result in object hallucination issues (i.e., generate objects that are inconsistent with target images in the descriptions). It either makes the current evaluation metric such as CIDEr for image captioning ineffective or generates wrong answers. Third, employing a multi-turn reasoning evaluation framework can mitigate the issue of object hallucination, shedding light on developing an effective pipeline for LVLM evaluation. The findings provide a foundational framework for the conception and assessment of innovative strategies aimed at enhancing zero-shot multimodal techniques. Our LVLM-eHub will be available at https://github.com/OpenGVLab/Multi-Modality-Arena

Can foundation models be guided to execute tasks involving legal reasoning? We believe that building a benchmark to answer this question will require sustained collaborative efforts between the computer science and legal communities. To that end, this short paper serves three purposes. First, we describe how IRAC-a framework legal scholars use to distinguish different types of legal reasoning-can guide the construction of a Foundation Model oriented benchmark. Second, we present a seed set of 44 tasks built according to this framework. We discuss initial findings, and highlight directions for new tasks. Finally-inspired by the Open Science movement-we make a call for the legal and computer science communities to join our efforts by contributing new tasks. This work is ongoing, and our progress can be tracked here: https://github.com/HazyResearch/legalbench.

Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from multiple potentially noisy supervision sources. However, proper measurement and analysis of these approaches remain a challenge. First, datasets used in existing works are often private and/or custom, limiting standardization. Second, WS datasets with the same name and base data often vary in terms of the labels and weak supervision sources used, a significant "hidden" source of evaluation variance. Finally, WS studies often diverge in terms of the evaluation protocol and ablations used. To address these problems, we introduce a benchmark platform, WRENCH, for thorough and standardized evaluation of WS approaches. It consists of 22 varied real-world datasets for classification and sequence tagging; a range of real, synthetic, and procedurally-generated weak supervision sources; and a modular, extensible framework for WS evaluation, including implementations for popular WS methods. We use WRENCH to conduct extensive comparisons over more than 120 method variants to demonstrate its efficacy as a benchmark platform. The code is available at https://github.com/JieyuZ2/wrench.

Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for research. We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data, and create a framework for the standardized evaluation of multiple object tracking methods. The benchmark is focused on multiple people tracking, since pedestrians are by far the most studied object in the tracking community, with applications ranging from robot navigation to self-driving cars. This paper collects the first three releases of the benchmark: (i) MOT15, along with numerous state-of-the-art results that were submitted in the last years, (ii) MOT16, which contains new challenging videos, and (iii) MOT17, that extends MOT16 sequences with more precise labels and evaluates tracking performance on three different object detectors. The second and third release not only offers a significant increase in the number of labeled boxes but also provide labels for multiple object classes beside pedestrians, as well as the level of visibility for every single object of interest. We finally provide a categorization of state-of-the-art trackers and a broad error analysis. This will help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light on potential future research directions.

Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative coherence, cover narrow domains, and only test simple recall-oriented tasks. This paper introduces a comprehensive solution to these challenges. First, we present a novel framework for automatically generating long (up to 10M tokens), coherent, and topically diverse conversations, accompanied by probing questions targeting a wide range of memory abilities. From this, we construct BEAM, a new benchmark comprising 100 conversations and 2,000 validated questions. Second, to enhance model performance, we propose LIGHT-a framework inspired by human cognition that equips LLMs with three complementary memory systems: a long-term episodic memory, a short-term working memory, and a scratchpad for accumulating salient facts. Our experiments on BEAM reveal that even LLMs with 1M token context windows (with and without retrieval-augmentation) struggle as dialogues lengthen. In contrast, LIGHT consistently improves performance across various models, achieving an average improvement of 3.5%-12.69% over the strongest baselines, depending on the backbone LLM. An ablation study further confirms the contribution of each memory component.

Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biological counterparts and show various agile skills to navigate complex environments quickly. Despite the interest, the field lacks systematic benchmarks to measure the performance of control policies and hardware in agility. We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. This encourages researchers to develop controllers that not only move fast, but do so in a controllable and versatile way. To set strong baselines, we present two methods for tackling the benchmark. In the first approach, we train specialist locomotion skills using on-policy reinforcement learning methods and combine them with a high-level navigation controller. In the second approach, we distill the specialist skills into a Transformer-based generalist locomotion policy, named Locomotion-Transformer, that can handle various terrains and adjust the robot's gait based on the perceived environment and robot states. Using a custom-built quadruped robot, we demonstrate that our method can complete the course at half the speed of a dog. We hope that our work represents a step towards creating controllers that enable robots to reach animal-level agility.

For more than a decade, researchers have measured progress in object recognition on ImageNet-based generalization benchmarks such as ImageNet-A, -C, and -R. Recent advances in foundation models, trained on orders of magnitude more data, have begun to saturate these standard benchmarks, but remain brittle in practice. This suggests standard benchmarks, which tend to focus on predefined or synthetic changes, may not be sufficient for measuring real world generalization. Consequently, we propose studying generalization across geography as a more realistic measure of progress using two datasets of objects from households across the globe. We conduct an extensive empirical evaluation of progress across nearly 100 vision models up to most recent foundation models. We first identify a progress gap between standard benchmarks and real-world, geographical shifts: progress on ImageNet results in up to 2.5x more progress on standard generalization benchmarks than real-world distribution shifts. Second, we study model generalization across geographies by measuring the disparities in performance across regions, a more fine-grained measure of real world generalization. We observe all models have large geographic disparities, even foundation CLIP models, with differences of 7-20% in accuracy between regions. Counter to modern intuition, we discover progress on standard benchmarks fails to improve geographic disparities and often exacerbates them: geographic disparities between the least performant models and today's best models have more than tripled. Our results suggest scaling alone is insufficient for consistent robustness to real-world distribution shifts. Finally, we highlight in early experiments how simple last layer retraining on more representative, curated data can complement scaling as a promising direction of future work, reducing geographic disparity on both benchmarks by over two-thirds.

Composed Image Retrieval (CIR) is a multimodal retrieval task where a query consists of a reference image and a textual modification, and the goal is to retrieve a target image satisfying both. In principle, strong performance on CIR benchmarks is assumed to require multimodal composition, i.e., combining complementary information from reference image and textual modification. In this work, we show that this assumption does not always hold. Across four widely used CIR benchmarks and eleven Generalist Multimodal Embedding models, a large fraction of queries can be solved using a single modality (from 32.2% to 83.6%), revealing pervasive unimodal shortcuts. Thus, high CIR performance can arise from unimodal signals rather than true multimodal composition. To better understand this issue, we perform a two-stage audit. First, we identify shortcut-solvable queries through cross-model analysis. Second, we conduct human validation on 4,741 shortcut-free queries, of which only 1,689 are well-formed, with common issues including ambiguous edits and mismatched targets. Re-evaluating models on this validated subset reveals qualitatively different behaviour: queries can no longer be solved with a single modality, and successful retrieval requires combining both inputs. While accuracy decreases, reliance on multimodal information increases. Overall, current CIR benchmarks conflate shortcut-solvable, noisy, and genuinely compositional queries, leading to an overestimation of model capability in multimodal composition.

Large language models have achieved striking results in interactive theorem proving, particularly in Lean. However, most benchmarks for LLM-based proof automation are drawn from mathematics in the Mathlib ecosystem, whereas proofs in software verification are developed inside definition-rich codebases with substantial project-specific libraries. We introduce VeriSoftBench, a benchmark of 500 Lean 4 proof obligations drawn from open-source formal-methods developments and packaged to preserve realistic repository context and cross-file dependencies. Our evaluation of frontier LLMs and specialized provers yields three observations. First, provers tuned for Mathlib-style mathematics transfer poorly to this repository-centric setting. Second, success is strongly correlated with transitive repository dependence: tasks whose proofs draw on large, multi-hop dependency closures are less likely to be solved. Third, providing curated context restricted to a proof's dependency closure improves performance relative to exposing the full repository, but nevertheless leaves substantial room for improvement. Our benchmark and evaluation suite are released at https://github.com/utopia-group/VeriSoftBench.

We present Agent-Diff, a novel benchmarking framework for evaluating agentic Large Language Models (LLMs) on real-world tasks that execute code via external APIs. Agentic LLM performance varies due to differences in models, external tool access, prompt structures, and agentic frameworks. Benchmarks must make fundamental trade-offs between a sandboxed approach that controls for variation in software environments and more ecologically valid approaches employing real services. Agent-Diff attempts to capture the desirable features of both of these approaches by including access to the real API interfaces for software services while sandboxing the environment in which calls are made, processed, and evaluated. This approach relies on two key innovations. The first is a novel state-diff contract, which separates process from outcome - rather than fuzzy trace or parameter matching, we define task success as whether the expected change in environment state was achieved. The second is a novel sandbox that provides a standardized scripting layer that all models use to execute code against external APIs (Slack, Box, Linear, Google Calendar). Thus, we can evaluate different agentic LLMs against a standardized set of contracts using a unified sandbox while still evaluating their performance on real-world service interfaces. Using the Agent-Diff framework, we provide benchmarks for nine LLMs across 224 tasks utilizing enterprise software workflows. In addition, we evaluate the robustness of the framework with ablation experiments to assess the contribution of access to API documentation on benchmark performance. Code and data: https://github.com/agent-diff-bench/agent-diff.

Code completion models have made significant progress in recent years. Recently, repository-level code completion has drawn more attention in modern software development, and several baseline methods and benchmarks have been proposed. However, existing repository-level code completion methods often fall short of fully using the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies. Besides, the existing benchmarks usually focus on limited code completion scenarios, which cannot reflect the repository-level code completion abilities well of existing methods. To address these limitations, we propose the R2C2-Coder to enhance and benchmark the real-world repository-level code completion abilities of code Large Language Models, where the R2C2-Coder includes a code prompt construction method R2C2-Enhance and a well-designed benchmark R2C2-Bench. Specifically, first, in R2C2-Enhance, we first construct the candidate retrieval pool and then assemble the completion prompt by retrieving from the retrieval pool for each completion cursor position. Second, based on R2C2 -Enhance, we can construct a more challenging and diverse R2C2-Bench with training, validation and test splits, where a context perturbation strategy is proposed to simulate the real-world repository-level code completion well. Extensive results on multiple benchmarks demonstrate the effectiveness of our R2C2-Coder.

Continual learning and few-shot learning are important frontiers in progress towards broader Machine Learning (ML) capabilities. There is a growing body of work in both, but few works combining the two. One exception is the Continual few-shot Learning (CFSL) framework of Antoniou et al. arXiv:2004.11967. In this study, we extend CFSL in two ways that capture a broader range of challenges, important for intelligent agent behaviour in real-world conditions. First, we modify CFSL to make it more comparable to standard continual learning experiments, where usually a much larger number of classes are presented. Second, we introduce an 'instance test' which requires recognition of specific instances of classes -- a capability of animal cognition that is usually neglected in ML. For an initial exploration of ML model performance under these conditions, we selected representative baseline models from the original CFSL work and added a model variant with replay. As expected, learning more classes is more difficult than the original CFSL experiments, and interestingly, the way in which image instances and classes are presented affects classification performance. Surprisingly, accuracy in the baseline instance test is comparable to other classification tasks, but poor given significant occlusion and noise. The use of replay for consolidation improves performance substantially for both types of tasks, but particularly the instance test.

Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of real-world environments. Second, they narrowly focus on mathematical problem-solving, neglecting the broader spectrum of reasoning skills -- including abstract, physical, planning, spatial, and temporal capabilities -- required for robust multimodal intelligence. Third, many benchmarks quickly saturate, offering limited headroom for diagnosing failure modes or measuring continued progress. We introduce MORSE-500 (Multimodal Reasoning Stress-test Environment), a video benchmark composed of 500 fully scripted clips with embedded questions spanning six complementary reasoning categories. Each instance is programmatically generated using deterministic Python scripts (via Manim, Matplotlib, MoviePy), generative video models, and curated real footage. This script-driven design allows fine-grained control over visual complexity, distractor density, and temporal dynamics -- enabling difficulty to be scaled systematically as models improve. Unlike static benchmarks that become obsolete once saturated, MORSE-500 is built to evolve: its controllable generation pipeline supports the creation of arbitrarily challenging new instances, making it ideally suited for stress-testing next-generation models. Initial experiments with state-of-the-art systems -- including various Gemini 2.5 Pro and OpenAI o3 which represent the strongest available at the time, alongside strong open-source models -- reveal substantial performance gaps across all categories, with particularly large deficits in abstract and planning tasks. We release the full dataset, generation scripts, and evaluation harness to support transparent, reproducible, and forward-looking multimodal reasoning research.

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench. a suite of 5,500 test cases across 10 country-language pairs, comprising a Jailbreak Benchmark of country-grounded adversarial prompts and a Cultural Benchmark where local sensitivities are embedded within innocuous requests. Each item is constructed via a multi-stage pipeline that combines LLM-assisted discovery, automated validation gates, and dual independent native-speaker annotators per country. To distinguish principled refusal from comprehension failure, we evaluate Attack Success Rate (ASR) alongside two complementary metrics we introduce: Neutral-Safe Rate (NSR) and Cultural Sensitivity Rate (CSR). Evaluating 10 frontier and 27 local LLMs reveals two key findings. First, jailbreak robustness and cultural awareness do not show a coupled relationship among frontier models, so a composite safety score obscures per-axis variation. Second, local models exhibit a near-linear ASR-NSR trade-off (r = -0.81), indicating that their apparent safety reflects generation failure rather than genuine alignment. XL-SafetyBench enables more nuanced, cross-cultural safety evaluation in the multilingual era.

Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) reward pixel fidelity over semantic correctness, while Frechet Video Distance (FVD) favors distributional textures over physical plausibility. Binary Visual Question Answering (VQA) based benchmarks like VBench~2.0 are prone to yes-bias and rely on low-resolution auditors that miss temporal failures. Moreover, their prompts target a single dimension at a time, multiplying the number of videos required while still not guaranteeing reliable results. WorldJen addresses these limitations directly. Binary VQA is replaced with Likert-scale questionnaires graded by a VLM that receives frames at native video resolution. Video generation costs are addressed by using adversarially curated prompts that are designed to exercise up to 16 quality dimensions simultaneously. The framework is built around two interlocking contributions. First, A blind human preference study is conducted, accumulating (2,696 pairwise annotations from 7 annotators with 100% pair coverage over 50 of the curated prompts times 6 state-of-the-art video models. A mean inter-annotator agreement of 66.9% is achieved and the study establishes a human ground-truth Bradley-Terry (BT) rating with a three-tier structure. Second, A VLM-as-a-judge evaluation engine using prompt-specific, dimension-specific Likert questionnaires (10 questions per dimension, 47,160 scored responses) judges the videos and reproduces the human-established three-tier BT rating structure independently. The VLM achieves a Spearman hatρ=1.000,~p=0.0014 that is interpreted as tier agreement with the human results. Six focused ablation studies validate the robustness of the VLM evaluation framework.

We introduce MRMR, the first expert-level multidisciplinary multimodal retrieval benchmark requiring intensive reasoning. MRMR contains 1,502 queries spanning 23 domains, with positive documents carefully verified by human experts. Compared to prior benchmarks, MRMR introduces three key advancements. First, it challenges retrieval systems across diverse areas of expertise, enabling fine-grained model comparison across domains. Second, queries are reasoning-intensive, with images requiring deeper interpretation such as diagnosing microscopic slides. We further introduce Contradiction Retrieval, a novel task requiring models to identify conflicting concepts. Finally, queries and documents are constructed as image-text interleaved sequences. Unlike earlier benchmarks restricted to single images or unimodal documents, MRMR offers a realistic setting with multi-image queries and mixed-modality corpus documents. We conduct an extensive evaluation of 4 categories of multimodal retrieval systems and 14 frontier models on MRMR. The text embedding model Qwen3-Embedding with LLM-generated image captions achieves the highest performance, highlighting substantial room for improving multimodal retrieval models. Although latest multimodal models such as Ops-MM-Embedding perform competitively on expert-domain queries, they fall short on reasoning-intensive tasks. We believe that MRMR paves the way for advancing multimodal retrieval in more realistic and challenging scenarios.

Recently, embedding resources, including models, benchmarks, and datasets, have been widely released to support a variety of languages. However, the Dutch language remains underrepresented, typically comprising only a small fraction of the published multilingual resources. To address this gap and encourage the further development of Dutch embeddings, we introduce new resources for their evaluation and generation. First, we introduce the Massive Text Embedding Benchmark for Dutch (MTEB-NL), which includes both existing Dutch datasets and newly created ones, covering a wide range of tasks. Second, we provide a training dataset compiled from available Dutch retrieval datasets, complemented with synthetic data generated by large language models to expand task coverage beyond retrieval. Finally, we release a series of E5-NL models compact yet efficient embedding models that demonstrate strong performance across multiple tasks. We make our resources publicly available through the Hugging Face Hub and the MTEB package.

We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks and demanding advanced coding skills in grounding and planning. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricate data processing and derive the answers. We set up the benchmark in a controllable and executable environment that aligns with real-world data analysis scenarios and is scalable. The annotators meticulously design the evaluation suite to ensure the accuracy and robustness of the evaluation. We develop the DA-Agent baseline. Experiments show that although the baseline performs better than other existing frameworks, using the current best LLMs achieves only 30.5% accuracy, leaving ample room for improvement. We release our benchmark at https://da-code-bench.github.io.

To bridge the gap between performance-oriented benchmarks and the evaluation of cognitively inspired models, we introduce BLiSS 1.0, a Benchmark of Learner Interlingual Syntactic Structure. Our benchmark operationalizes a new paradigm of selective tolerance, testing whether a model finds a naturalistic learner error more plausible than a matched, artificial error within the same sentence. Constructed from over 2.8 million naturalistic learner sentences, BLiSS provides 136,867 controlled triplets (corrected, learner, artificial) for this purpose. Experiments on a diverse suite of models demonstrate that selective tolerance is a distinct capability from standard grammaticality, with performance clustering strongly by training paradigm. This validates BLiSS as a robust tool for measuring how different training objectives impact a model's alignment with the systematic patterns of human language acquisition.

Considerable advancements have been achieved in SLAM methods tailored for structured environments, yet their robustness under challenging corner cases remains a critical limitation. Although multi-sensor fusion approaches integrating diverse sensors have shown promising performance improvements, the research community faces two key barriers: On one hand, the lack of standardized and configurable benchmarks that systematically evaluate SLAM algorithms under diverse degradation scenarios hinders comprehensive performance assessment. While on the other hand, existing SLAM frameworks primarily focus on fusing a limited set of sensor types, without effectively addressing adaptive sensor selection strategies for varying environmental conditions. To bridge these gaps, we make three key contributions: First, we introduce M3DGR dataset: a sensor-rich benchmark with systematically induced degradation patterns including visual challenge, LiDAR degeneracy, wheel slippage and GNSS denial. Second, we conduct a comprehensive evaluation of forty SLAM systems on M3DGR, providing critical insights into their robustness and limitations under challenging real-world conditions. Third, we develop a resilient modular multi-sensor fusion framework named Ground-Fusion++, which demonstrates robust performance by coupling GNSS, RGB-D, LiDAR, IMU (Inertial Measurement Unit) and wheel odometry. Codes and datasets are publicly available.

Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their capabilities in emotional reasoning remain limited. The field currently suffers from a scarcity of large-scale datasets with high-quality, descriptive emotion annotations and lacks standardized benchmarks for evaluation. Our preliminary framework, Emotion-LLaMA, pioneered instruction-tuned multimodal learning for emotion reasoning but was restricted by explicit face detectors, implicit fusion strategies, and low-quality training data with limited scale. To address these limitations, we present Emotion-LLaMAv2 and the MMEVerse benchmark, establishing an end-to-end pipeline together with a standardized evaluation setting for emotion recognition and reasoning. Emotion-LLaMAv2 introduces three key advances. First, an end-to-end multiview encoder eliminates external face detection and captures nuanced emotional cues via richer spatial and temporal multiview tokens. Second, a Conv Attention pre-fusion module is designed to enable simultaneous local and global multimodal feature interactions external to the LLM backbone. Third, a perception-to-cognition curriculum instruction tuning scheme within the LLaMA2 backbone unifies emotion recognition and free-form emotion reasoning. To support large-scale training and reproducible evaluation, MMEVerse aggregates twelve publicly available emotion datasets, including IEMOCAP, MELD, DFEW, and MAFW, into a unified multimodal instruction format. The data are re-annotated via a multi-agent pipeline involving Qwen2 Audio, Qwen2.5 VL, and GPT 4o, producing 130k training clips and 36k testing clips across 18 evaluation benchmarks.

Embodied Planning is dedicated to the goal of creating agents capable of executing long-horizon tasks in complex physical worlds. However, existing embodied planning benchmarks frequently feature short-horizon tasks and coarse-grained action primitives. To address this challenge, we introduce CookBench, a benchmark for long-horizon planning in complex cooking scenarios. By leveraging a high-fidelity simulation environment built upon the powerful Unity game engine, we define frontier AI challenges in a complex, realistic environment. The core task in CookBench is designed as a two-stage process. First, in Intention Recognition, an agent needs to accurately parse a user's complex intent. Second, in Embodied Interaction, the agent should execute the identified cooking goal through a long-horizon, fine-grained sequence of physical actions. Unlike existing embodied planning benchmarks, we refine the action granularity to a spatial level that considers crucial operational information while abstracting away low-level robotic control. Besides, We provide a comprehensive toolset that encapsulates the simulator. Its unified API supports both macro-level operations, such as placing orders and purchasing ingredients, and a rich set of fine-grained embodied actions for physical interaction, enabling researchers to focus on high-level planning and decision-making. Furthermore, we present an in-depth analysis of state-of-the-art, closed-source Large Language Model and Vision-Language Model, revealing their major shortcomings and challenges posed by complex, long-horizon tasks. The full benchmark will be open-sourced to facilitate future research.

Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency. However, these documents are often lengthy, structurally diverse, and multimodal, comprising dense text, structured tables, complex figures, and layout-dependent semantics. Existing AI systems often struggle to perform reliable document-level reasoning in such settings, and no dedicated benchmark currently exists in ESG domain. To fill the gap, we introduce MMESGBench, a first-of-its-kind benchmark dataset targeted to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents. This dataset is constructed via a human-AI collaborative, multi-stage pipeline. First, a multimodal LLM generates candidate question-answer (QA) pairs by jointly interpreting rich textual, tabular, and visual information from layout-aware document pages. Second, an LLM verifies the semantic accuracy, completeness, and reasoning complexity of each QA pair. This automated process is followed by an expert-in-the-loop validation, where domain specialists validate and calibrate QA pairs to ensure quality, relevance, and diversity. MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories. Questions are categorized as single-page, cross-page, or unanswerable, with each accompanied by fine-grained multimodal evidence. Initial experiments validate that multimodal and retrieval-augmented models substantially outperform text-only baselines, particularly on visually grounded and cross-page tasks. MMESGBench is publicly available as an open-source dataset at https://github.com/Zhanglei1103/MMESGBench.

AI-driven video generation techniques have made significant progress in recent years. However, AI-generated videos (AGVs) involving human activities often exhibit substantial visual and semantic distortions, hindering the practical application of video generation technologies in real-world scenarios. To address this challenge, we conduct a pioneering study on human activity AGV quality assessment, focusing on visual quality evaluation and the identification of semantic distortions. First, we construct the AI-Generated Human activity Video Quality Assessment (Human-AGVQA) dataset, consisting of 3,200 AGVs derived from 8 popular text-to-video (T2V) models using 400 text prompts that describe diverse human activities. We conduct a subjective study to evaluate the human appearance quality, action continuity quality, and overall video quality of AGVs, and identify semantic issues of human body parts. Based on Human-AGVQA, we benchmark the performance of T2V models and analyze their strengths and weaknesses in generating different categories of human activities. Second, we develop an objective evaluation metric, named AI-Generated Human activity Video Quality metric (GHVQ), to automatically analyze the quality of human activity AGVs. GHVQ systematically extracts human-focused quality features, AI-generated content-aware quality features, and temporal continuity features, making it a comprehensive and explainable quality metric for human activity AGVs. The extensive experimental results show that GHVQ outperforms existing quality metrics on the Human-AGVQA dataset by a large margin, demonstrating its efficacy in assessing the quality of human activity AGVs. The Human-AGVQA dataset and GHVQ metric will be released in public at https://github.com/zczhang-sjtu/GHVQ.git

CPU performance prediction, which involves forecasting the performance scores of a CPU based on its hardware characteristics during its operation, is a critical technology for computational system design and resource management in the big data era. However, this research field currently faces two significant challenges. First, collecting real-world data is challenging due to the wide variety of CPU products on the market and the highly specialized nature of relevant hardware characteristics. In the research process, this field lacks a standard dataset with unified hardware characteristics, wide data coverage, and comprehensive benchmarks. Second, existing methods based on hardware simulation models or machine learning exhibit notable shortcomings, such as lengthy simulation test cycles and low prediction accuracy. To bridge these gaps, we first collect, preprocess, and standardize historical data from the 4th Generation Intel Xeon Scalable Processors across multiple benchmark suites to create a new dataset, named PerfCastDB. Subsequently, we design a deep learning based model called Nova CPU Performance Predictor (NCPP) as the baseline for this new dataset. The NCPP network is designed based on group attention mechanism. It effectively quantifies the implicit relationships between hardware characteristics within and across groups and comprehensively models the impact of various hardware characteristics on CPU performance prediction. We conduct comparative experiments using the proposed PerfCastDB dataset. Compared to existing approaches, NCPP achieves superior evaluation results, demonstrating its effectiveness. Furthermore, we have open-sourced part of the dataset and the NCPP network code to facilitate subsequent research. The resources can be accessed at https://github.com/xiaoman-liu/NCPP.

Large Language Models (LLMs) have demonstrated remarkable performance on coding related tasks, particularly on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities of LLMs suffer from severe limitations. First, most benchmarks are deficient as they focus on a narrow range of popular programming languages and specific tasks, whereas the real-world software development scenarios show dire need to implement systems with multilingual programming environments to satisfy diverse requirements. Practical programming practices also strongly expect multi-task settings for testing coding capabilities of LLMs comprehensively and robustly. Second, most benchmarks also fail to consider the actual executability and the consistency of execution results of the generated code. To bridge these gaps between existing benchmarks and expectations from practical applications, we introduce CodeScope, an execution-based, multilingual, multi-task, multi-dimensional evaluation benchmark for comprehensively gauging LLM capabilities on coding tasks. CodeScope covers 43 programming languages and 8 coding tasks. It evaluates the coding performance of LLMs from three dimensions (perspectives): difficulty, efficiency, and length. To facilitate execution-based evaluations of code generation, we develop MultiCodeEngine, an automated code execution engine that supports 14 programming languages. Finally, we systematically evaluate and analyze 8 mainstream LLMs on CodeScope tasks and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks. The CodeScope benchmark and datasets are publicly available at https://github.com/WeixiangYAN/CodeScope.

Geometric information in the normalized digital surface models (nDSM) is highly correlated with the semantic class of the land cover. Exploiting two modalities (RGB and nDSM (height)) jointly has great potential to improve the segmentation performance. However, it is still an under-explored field in remote sensing due to the following challenges. First, the scales of existing datasets are relatively small and the diversity of existing datasets is limited, which restricts the ability of validation. Second, there is a lack of unified benchmarks for performance assessment, which leads to difficulties in comparing the effectiveness of different models. Last, sophisticated multi-modal semantic segmentation methods have not been deeply explored for remote sensing data. To cope with these challenges, in this paper, we introduce a new remote-sensing benchmark dataset for multi-modal semantic segmentation based on RGB-Height (RGB-H) data. Towards a fair and comprehensive analysis of existing methods, the proposed benchmark consists of 1) a large-scale dataset including co-registered RGB and nDSM pairs and pixel-wise semantic labels; 2) a comprehensive evaluation and analysis of existing multi-modal fusion strategies for both convolutional and Transformer-based networks on remote sensing data. Furthermore, we propose a novel and effective Transformer-based intermediary multi-modal fusion (TIMF) module to improve the semantic segmentation performance through adaptive token-level multi-modal fusion.The designed benchmark can foster future research on developing new methods for multi-modal learning on remote sensing data. Extensive analyses of those methods are conducted and valuable insights are provided through the experimental results. Code for the benchmark and baselines can be accessed at https://github.com/EarthNets/RSI-MMSegmentation.

We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000 incorporates three core features. First, our problems reflect diverse, realistic, and practical use cases since we collected them from StackOverflow. Second, our automatic evaluation is highly specific (reliable) -- across all Codex-002-predicted solutions that our evaluation accept, only 1.8% of them are incorrect; we achieve this with multi-criteria metrics, checking both functional correctness by running test cases and surface-form constraints by restricting API usages or keywords. Finally, we proactively defend against memorization by slightly modifying our problems to be different from the original StackOverflow source; consequently, models cannot answer them correctly by memorizing the solutions from pre-training. The current best public system (Codex-002) achieves 43.3% accuracy, leaving ample room for improvement. We release our benchmark at https://ds1000-code-gen.github.io.

Visual place recognition (VPR) is critical in not only localization and mapping for autonomous driving vehicles, but also in assistive navigation for the visually impaired population. To enable a long-term VPR system on a large scale, several challenges need to be addressed. First, different applications could require different image view directions, such as front views for self-driving cars while side views for the low vision people. Second, VPR in metropolitan scenes can often cause privacy concerns due to the imaging of pedestrian and vehicle identity information, calling for the need for data anonymization before VPR queries and database construction. Both factors could lead to VPR performance variations that are not well understood yet. To study their influences, we present the NYU-VPR dataset that contains more than 200,000 images over a 2km by 2km area near the New York University campus, taken within the whole year of 2016. We present benchmark results on several popular VPR algorithms showing that side views are significantly more challenging for current VPR methods while the influence of data anonymization is almost negligible, together with our hypothetical explanations and in-depth analysis.

The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic workflows. However, reliable evaluation has emerged as a critical bottleneck. Existing benchmarks predominantly evaluate ''whether it is right'' (basic prompt-following) while fundamentally neglecting ''whether it is good'' (cinematic quality, acting, and aesthetics). Furthermore, current automated metrics lack the domain-specific rigor required to provide trustworthy signals, creating a severe credibility gap between human aesthetic perception and machine scoring. To bridge this gap, we introduce EvalVerse, a comprehensive, pipeline-aware, and expert-calibrated evaluation framework. We treat video generation assessment not merely as an engineering task, but as a core scientific problem: the systematic digitization of subjective cinematic expertise. First, we organize domain knowledge into an evaluation taxonomy aligned with the professional filmmaking workflow (pre-production, production, and post-production). Second, we distill human expert judgments into a curated dataset with large-scale human annotations. Third, we inject this knowledge into Vision-Language Models (VLMs) through an expert-calibrated fine-tuning strategy, enabling the VLM to perform explicit Chain-of-Thought reasoning. Compared to previous works, EvalVerse not only retains compatibility with foundational ''rightness'' metrics, but also significantly expands the criteria to ''goodness'' and broaden the task coverage to complex multi-shot sequencing and audio-visual integration. Consequently, by providing granular diagnostic signals, EvalVerse transcends a static leaderboard and establishes a fundamental infrastructure for future work, such as reward models and evaluator agent.

Retrieval-augmented generation (RAG) augments large language models (LLM) by retrieving relevant knowledge, showing promising potential in mitigating LLM hallucinations and enhancing response quality, thereby facilitating the great adoption of LLMs in practice. However, we find that existing RAG systems are inadequate in answering multi-hop queries, which require retrieving and reasoning over multiple pieces of supporting evidence. Furthermore, to our knowledge, no existing RAG benchmarking dataset focuses on multi-hop queries. In this paper, we develop a novel dataset, MultiHop-RAG, which consists of a knowledge base, a large collection of multi-hop queries, their ground-truth answers, and the associated supporting evidence. We detail the procedure of building the dataset, utilizing an English news article dataset as the underlying RAG knowledge base. We demonstrate the benchmarking utility of MultiHop-RAG in two experiments. The first experiment compares different embedding models for retrieving evidence for multi-hop queries. In the second experiment, we examine the capabilities of various state-of-the-art LLMs, including GPT-4, PaLM, and Llama2-70B, in reasoning and answering multi-hop queries given the evidence. Both experiments reveal that existing RAG methods perform unsatisfactorily in retrieving and answering multi-hop queries. We hope MultiHop-RAG will be a valuable resource for the community in developing effective RAG systems, thereby facilitating greater adoption of LLMs in practice. The MultiHop-RAG and implemented RAG system is publicly available at https://github.com/yixuantt/MultiHop-RAG/.

Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effortlessly process many originally exhausting tasks -- e.g., digesting a long-form document to find answers vs. directly asking an LLM about it. However, existing real-task-based long-context evaluation benchmarks have two major shortcomings. First, benchmarks like LongBench often do not provide proper metrics to separate long-context performance from the model's baseline ability, making cross-model comparison unclear. Second, such benchmarks are usually constructed with fixed input lengths, which limits their applicability across different models and fails to reveal when a model begins to break down. To address these issues, we introduce a length-controllable long-context benchmark and a novel metric that disentangles baseline knowledge from true long-context capabilities. Experiments demonstrate the superiority of our approach in effectively evaluating LLMs.

Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergence of new cultural datasets. However, these datasets frequently fall short of providing cultural reasoning while underrepresenting many cultures. In this paper, we introduce the Seeing Culture Benchmark (SCB), focusing on cultural reasoning with a novel approach that requires VLMs to reason on culturally rich images in two stages: i) selecting the correct visual option with multiple-choice visual question answering (VQA), and ii) segmenting the relevant cultural artifact as evidence of reasoning. Visual options in the first stage are systematically organized into three types: those originating from the same country, those from different countries, or a mixed group. Notably, all options are derived from a singular category for each type. Progression to the second stage occurs only after a correct visual option is chosen. The SCB benchmark comprises 1,065 images that capture 138 cultural artifacts across five categories from seven Southeast Asia countries, whose diverse cultures are often overlooked, accompanied by 3,178 questions, of which 1,093 are unique and meticulously curated by human annotators. Our evaluation of various VLMs reveals the complexities involved in cross-modal cultural reasoning and highlights the disparity between visual reasoning and spatial grounding in culturally nuanced scenarios. The SCB serves as a crucial benchmark for identifying these shortcomings, thereby guiding future developments in the field of cultural reasoning. https://github.com/buraksatar/SeeingCulture

Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially modified, while subtle yet consequential edits outside the mask are treated as natural. We reformulate VLM image tampering from coarse region labels to a pixel-grounded, meaning and language-aware task. First, we introduce a taxonomy spanning edit primitives (replace/remove/splice/inpaint/attribute/colorization, etc.) and their semantic class of tampered object, linking low-level changes to high-level understanding. Second, we release a new benchmark with per-pixel tamper maps and paired category supervision to evaluate detection and classification within a unified protocol. Third, we propose a training framework and evaluation metrics that quantify pixel-level correctness with localization to assess confidence or prediction on true edit intensity, and further measure tamper meaning understanding via semantics-aware classification and natural language descriptions for the predicted regions. We also re-evaluate the existing strong segmentation/localization baselines on recent strong tamper detectors and reveal substantial over- and under-scoring using mask-only metrics, and expose failure modes on micro-edits and off-mask changes. Our framework advances the field from masks to pixels, meanings and language descriptions, establishing a rigorous standard for tamper localization, semantic classification and description. Code and benchmark data are available at https://github.com/VILA-Lab/PIXAR.

Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs associated with expert annotation. Currently, no publicly available dataset or benchmark encompasses various types of surgical wounds, resulting in the absence of an open-source Surgical-Wound screening tool. To address this gap: (1) we present SurgWound, the first open-source dataset featuring a diverse array of surgical wound types. It contains 697 surgical wound images annotated by 3 professional surgeons with eight fine-grained clinical attributes. (2) Based on SurgWound, we introduce the first benchmark for surgical wound diagnosis, which includes visual question answering (VQA) and report generation tasks to comprehensively evaluate model performance. (3) Furthermore, we propose a three-stage learning framework, WoundQwen, for surgical wound diagnosis. In the first stage, we employ five independent MLLMs to accurately predict specific surgical wound characteristics. In the second stage, these predictions serve as additional knowledge inputs to two MLLMs responsible for diagnosing outcomes, which assess infection risk and guide subsequent interventions. In the third stage, we train a MLLM that integrates the diagnostic results from the previous two stages to produce a comprehensive report. This three-stage framework can analyze detailed surgical wound characteristics and provide subsequent instructions to patients based on surgical images, paving the way for personalized wound care, timely intervention, and improved patient outcomes.

LLMs' capabilities are enhanced by using function calls to integrate various data sources or API results into the context window. Typical tools include search, web crawlers, maps, financial data, file systems, and browser usage, etc. Integrating these data sources or functions requires a standardized method. The Model Context Protocol (MCP) provides a standardized way to supply context to LLMs. However, the evaluation of LLMs and AI Agents' MCP tool use abilities suffer from several issues. First, there's a lack of comprehensive datasets or benchmarks to evaluate various MCP tools. Second, the diverse formats of response from MCP tool call execution further increase the difficulty of evaluation. Additionally, unlike existing tool-use benchmarks with high success rates in functions like programming and math functions, the success rate of real-world MCP tool is not guaranteed and varies across different MCP servers. Furthermore, the LLMs' context window also limits the number of available tools that can be called in a single run, because the textual descriptions of tool and the parameters have long token length for an LLM to process all at once. To help address the challenges of evaluating LLMs' performance on calling MCP tools, we propose MCPToolBench++, a large-scale, multi-domain AI Agent tool use benchmark. As of July 2025, this benchmark is build upon marketplace of over 4k MCP servers from more than 40 categories, collected from the MCP marketplaces and GitHub communities. The datasets consist of both single-step and multi-step tool calls across different categories. We evaluated SOTA LLMs with agentic abilities on this benchmark and reported the results.

We introduce LexBench, a comprehensive evaluation suite enabled to test language models (LMs) on ten semantic phrase processing tasks. Unlike prior studies, it is the first work to propose a framework from the comparative perspective to model the general semantic phrase (i.e., lexical collocation) and three fine-grained semantic phrases, including idiomatic expression, noun compound, and verbal construction. Thanks to \ourbenchmark, we assess the performance of 15 LMs across model architectures and parameter scales in classification, extraction, and interpretation tasks. Through the experiments, we first validate the scaling law and find that, as expected, large models excel better than the smaller ones in most tasks. Second, we investigate further through the scaling semantic relation categorization and find that few-shot LMs still lag behind vanilla fine-tuned models in the task. Third, through human evaluation, we find that the performance of strong models is comparable to the human level regarding semantic phrase processing. Our benchmarking findings can serve future research aiming to improve the generic capability of LMs on semantic phrase comprehension. Our source code and data are available at https://github.com/jacklanda/LexBench

Recent research has demonstrated that Large Language Models (LLMs) can enhance their capabilities by utilizing external tools. However, three pivotal questions remain unanswered: (1) How effective are current LLMs in utilizing tools? (2) How can we enhance LLMs' ability to utilize tools? (3) What obstacles need to be overcome to leverage tools? To address these questions, we introduce API-Bank, a groundbreaking benchmark, specifically designed for tool-augmented LLMs. For the first question, we develop a runnable evaluation system consisting of 73 API tools. We annotate 314 tool-use dialogues with 753 API calls to assess the existing LLMs' capabilities in planning, retrieving, and calling APIs. For the second question, we construct a comprehensive training set containing 1,888 tool-use dialogues from 2,138 APIs spanning 1,000 distinct domains. Using this dataset, we train Lynx, a tool-augmented LLM initialized from Alpaca. Experimental results demonstrate that GPT-3.5 exhibits improved tool utilization compared to GPT-3, while GPT-4 excels in planning. However, there is still significant potential for further improvement. Moreover, Lynx surpasses Alpaca's tool utilization performance by more than 26 pts and approaches the effectiveness of GPT-3.5. Through error analysis, we highlight the key challenges for future research in this field to answer the third question.

Social media platforms often foster environments where users primarily engage with content that aligns with their existing beliefs, thereby reinforcing their views and limiting exposure to opposing viewpoints. In this paper, we analyze X (formerly Twitter) discussions on climate change throughout 2019, using an unsupervised method centered on chambers--second-order information sources--to uncover ideological patterns at scale. Beyond direct connections, chambers capture shared sources of influence, revealing polarization dynamics efficiently and effectively. Analyzing retweet patterns, we identify echo chambers of climate believers and skeptics, revealing strong chamber overlap within ideological groups and minimal overlap between them, resulting in a robust bimodal structure that characterizes polarization. Our method enables us to infer the stance of high-impact users based on their audience's chamber alignment, allowing for the classification of over half the retweeting population with minimal cross-group interaction, in what we term augmented echo chamber classification. We benchmark our approach against manual labeling and a state-of-the-art latent ideology model, finding comparable performance but with nearly four times greater coverage. Moreover, we find that echo chamber structures remain stable over time, even as their members change significantly, suggesting that these structures are a persistent and emergent property of the system. Notably, polarization decreases and climate skepticism rises during the #FridaysForFuture strikes in September 2019. This chamber-based analysis offers valuable insights into the persistence and fluidity of ideological polarization on social media.

Scene text detection has seen the emergence of high-performing methods that excel on academic benchmarks. However, these detectors often fail to replicate such success in real-world scenarios. We uncover two key factors contributing to this discrepancy through extensive experiments. First, a Fine-tuning Gap, where models leverage Dataset-Specific Optimization (DSO) paradigm for one domain at the cost of reduced effectiveness in others, leads to inflated performances on academic benchmarks. Second, the suboptimal performance in practical settings is primarily attributed to the long-tailed distribution of texts, where detectors struggle with rare and complex categories as artistic or overlapped text. Given that the DSO paradigm might undermine the generalization ability of models, we advocate for a Joint-Dataset Learning (JDL) protocol to alleviate the Fine-tuning Gap. Additionally, an error analysis is conducted to identify three major categories and 13 subcategories of challenges in long-tailed scene text, upon which we propose a Long-Tailed Benchmark (LTB). LTB facilitates a comprehensive evaluation of ability to handle a diverse range of long-tailed challenges. We further introduce MAEDet, a self-supervised learning-based method, as a strong baseline for LTB. The code is available at https://github.com/pd162/LTB.

While ViTs have achieved across machine learning tasks, deploying them in real-world scenarios faces a critical challenge: generalizing under OoD shifts. A crucial research gap exists in understanding how to design ViT architectures, both manually and automatically, for better OoD generalization. To this end, we introduce OoD-ViT-NAS, the first systematic benchmark for ViTs NAS focused on OoD generalization. This benchmark includes 3000 ViT architectures of varying computational budgets evaluated on 8 common OoD datasets. Using this benchmark, we analyze factors contributing to OoD generalization. Our findings reveal key insights. First, ViT architecture designs significantly affect OoD generalization. Second, ID accuracy is often a poor indicator of OoD accuracy, highlighting the risk of optimizing ViT architectures solely for ID performance. Third, we perform the first study of NAS for ViTs OoD robustness, analyzing 9 Training-free NAS methods. We find that existing Training-free NAS methods are largely ineffective in predicting OoD accuracy despite excelling at ID accuracy. Simple proxies like Param or Flop surprisingly outperform complex Training-free NAS methods in predicting OoD accuracy. Finally, we study how ViT architectural attributes impact OoD generalization and discover that increasing embedding dimensions generally enhances performance. Our benchmark shows that ViT architectures exhibit a wide range of OoD accuracy, with up to 11.85% improvement for some OoD shifts. This underscores the importance of studying ViT architecture design for OoD. We believe OoD-ViT-NAS can catalyze further research into how ViT designs influence OoD generalization.

Following the successful 2023 edition, we organised the Second Perception Test challenge as a half-day workshop alongside the IEEE/CVF European Conference on Computer Vision (ECCV) 2024, with the goal of benchmarking state-of-the-art video models and measuring the progress since last year using the Perception Test benchmark. This year, the challenge had seven tracks (up from six last year) and covered low-level and high-level tasks, with language and non-language interfaces, across video, audio, and text modalities; the additional track covered hour-long video understanding and introduced a novel video QA benchmark 1h-walk VQA. Overall, the tasks in the different tracks were: object tracking, point tracking, temporal action localisation, temporal sound localisation, multiple-choice video question-answering, grounded video question-answering, and hour-long video question-answering. We summarise in this report the challenge tasks and results, and introduce in detail the novel hour-long video QA benchmark 1h-walk VQA.

Anomaly detection (AD) is a machine learning task that identifies anomalies by learning patterns from normal training data. In many real-world scenarios, anomalies vary in severity, from minor anomalies with little risk to severe abnormalities requiring immediate attention. However, existing models primarily operate in a binary setting, and the anomaly scores they produce are usually based on the deviation of data points from normal data, which may not accurately reflect practical severity. In this paper, we address this gap by making three key contributions. First, we propose a novel setting, Multilevel AD (MAD), in which the anomaly score represents the severity of anomalies in real-world applications, and we highlight its diverse applications across various domains. Second, we introduce a novel benchmark, MAD-Bench, that evaluates models not only on their ability to detect anomalies, but also on how effectively their anomaly scores reflect severity. This benchmark incorporates multiple types of baselines and real-world applications involving severity. Finally, we conduct a comprehensive performance analysis on MAD-Bench. We evaluate models on their ability to assign severity-aligned scores, investigate the correspondence between their performance on binary and multilevel detection, and study their robustness. This analysis offers key insights into improving AD models for practical severity alignment. The code framework and datasets used for the benchmark will be made publicly available.