Daily Papers

Mixture-of-experts (MoE) architectures enable scaling large language models (LLMs) to vast parameter counts without a proportional rise in computational costs. However, the significant memory demands of large MoE models hinder their deployment across various computational environments, from cloud servers to consumer devices. This study first demonstrates pronounced task-specific specialization in expert activation patterns within MoE layers. Building on this, we introduce PreMoe, a novel framework that enables efficient deployment of massive MoE models in memory-constrained environments. PreMoe features two main components: probabilistic expert pruning (PEP) and task-adaptive expert retrieval (TAER). PEP employs a new metric, the task-conditioned expected selection score (TCESS), derived from router logits to quantify expert importance for specific tasks, thereby identifying a minimal set of critical experts. TAER leverages these task-specific expert importance profiles for efficient inference. It pre-computes and stores compact expert patterns for diverse tasks. When a user query is received, TAER rapidly identifies the most relevant stored task pattern and reconstructs the model by loading only the small subset of experts crucial for that task. This approach dramatically reduces the memory footprint across all deployment scenarios. DeepSeek-R1 671B maintains 97.2\% accuracy on MATH500 when pruned to 8/128 configuration (50\% expert reduction), and still achieves 72.0\% with aggressive 8/32 pruning (87.5\% expert reduction). Pangu-Ultra-MoE 718B achieves 97.15\% on MATH500 and 81.3\% on AIME24 with 8/128 pruning, while even more aggressive pruning to 4/64 (390GB memory) preserves 96.95\% accuracy on MATH500. We make our code publicly available at https://github.com/JarvisPei/PreMoe.

The burgeoning field of foundation models necessitates advanced data processing mechanisms capable of harnessing vast and valuable data with various types used by these models. Nevertheless, the current landscape presents unique challenges that traditional data processing frameworks struggle to handle effectively, particularly in handling the complexity of multimodal data. In response, we present Data-Juicer 2.0, a data processing system backed by 100+ data processing operators spanning text, image, video, and audio modalities, supporting more critical tasks including data analysis, synthesis, annotation, and foundation model post-training. With seamless compatibility and dedicated optimization for popular dataset hubs like Hugging Face and computing engines like Ray, it improves upon its predecessor in terms of usability, efficiency, and programmability. It features an easily accessible user interface layer that supports decoupled Python interactions, RESTful APIs, and conversational commands. It contains a new runtime layer optimized for adaptive execution and management across varying dataset scales, processing demands, and computational environments, while hiding unnecessary system details. Extensive empirical evaluations demonstrate Data-Juicer 2.0's remarkable performance and scalability, highlighting its capability to efficiently process TB-level data with 10k+ CPU cores. The system is publicly available and has been widely adopted in diverse research fields and real-world products such as Alibaba Cloud PAI. We actively maintain it and share insights from practical feedback, with the goal of facilitating research and application of next-generation foundation models.

As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code agents have demonstrated sophisticated skills in agentic coding and reasoning, suggesting that code execution can serve as a scalable environment for mathematical experimentation. In this paper, we investigate the potential of code agents to autonomously evolve existing math problems into more complex variations. We introduce a multi-agent framework designed to perform problem evolution while validating the solvability and increased difficulty of the generated problems. Our experiments demonstrate that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals. This work provides empirical evidence that code-driven agents can serve as a viable mechanism for synthesizing high-difficulty mathematical reasoning problems within scalable computational environments. Our data is available at https://github.com/TarferSoul/Code2Math.

We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can be learned from training on static code alone, we mid-train CWM on a large amount of observation-action trajectories from Python interpreter and agentic Docker environments, and perform extensive multi-task reasoning RL in verifiable coding, math, and multi-turn software engineering environments. With CWM, we provide a strong testbed for researchers to explore the opportunities world modeling affords for improving code generation with reasoning and planning in computational environments. We present first steps of how world models can benefit agentic coding, enable step-by-step simulation of Python code execution, and show early results of how reasoning can benefit from the latter. CWM is a dense, decoder-only LLM trained with a context size of up to 131k tokens. Independent of its world modeling capabilities, CWM offers strong performance on general coding and math tasks: it reaches pass@1 scores of 65.8% on SWE-bench Verified (with test-time scaling), 68.6% on LiveCodeBench, 96.6% on Math-500, and 76.0% on AIME 2024. To support further research on code world modeling, we release model checkpoints after mid-training, SFT, and RL.

The complexity of modern bioinformatics analysis has created a critical gap between data generation and developing scientific insights. While large language models (LLMs) have shown promise in scientific reasoning, they remain fundamentally limited when dealing with real-world analytical workflows that demand iterative computation, tool integration and rigorous validation. We introduce K-Dense Analyst, a hierarchical multi-agent system that achieves autonomous bioinformatics analysis through a dual-loop architecture. K-Dense Analyst, part of the broader K-Dense platform, couples planning with validated execution using specialized agents to decompose complex objectives into executable, verifiable tasks within secure computational environments. On BixBench, a comprehensive benchmark for open-ended biological analysis, K-Dense Analyst achieves 29.2% accuracy, surpassing the best-performing language model (GPT-5) by 6.3 percentage points, representing nearly 27% improvement over what is widely considered the most powerful LLM available. Remarkably, K-Dense Analyst achieves this performance using Gemini 2.5 Pro, which attains only 18.3% accuracy when used directly, demonstrating that our architectural innovations unlock capabilities far beyond the underlying model's baseline performance. Our insights demonstrate that autonomous scientific reasoning requires more than enhanced language models, it demands purpose-built systems that can bridge the gap between high-level scientific objectives and low-level computational execution. These results represent a significant advance toward fully autonomous computational biologists capable of accelerating discovery across the life sciences.

Multi-robot systems require scalable and federated methods to model complex environments under computational and communication constraints. Gaussian Processes (GPs) offer robust probabilistic modeling, but suffer from cubic computational complexity, limiting their applicability in large-scale deployments. To address this challenge, we introduce the pxpGP, a novel distributed GP framework tailored for both centralized and decentralized large-scale multi-robot networks. Our approach leverages sparse variational inference to generate a local compact pseudo-representation. We introduce a sparse variational optimization scheme that bounds local pseudo-datasets and formulate a global scaled proximal-inexact consensus alternating direction method of multipliers (ADMM) with adaptive parameter updates and warm-start initialization. Experiments on synthetic and real-world datasets demonstrate that pxpGP and its decentralized variant, dec-pxpGP, outperform existing distributed GP methods in hyperparameter estimation and prediction accuracy, particularly in large-scale networks.

This paper introduces the first two-dimensional XOR-based secret sharing scheme for layered multipath communication networks. We present a construction that guarantees successful message recovery and perfect privacy when an adversary observes and disrupts any single path at each transmission layer. The scheme achieves information-theoretic security using only bitwise XOR operations with linear O(|S|) complexity, where |S| is the message length. We provide mathematical proofs demonstrating that the scheme maintains unconditional security regardless of computational resources available to adversaries. Unlike encryption-based approaches vulnerable to quantum computing advances, our construction offers provable security suitable for resource-constrained military environments where computational assumptions may fail.

Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry.

Modern socio-technical systems increasingly involve multi-stakeholder environments where actors simultaneously cooperate and compete. These coopetitive relationships exhibit dynamic trust evolution based on observed behavior over repeated interactions. While conceptual modeling languages like i* represent trust relationships qualitatively, they lack computational mechanisms for analyzing how trust changes with behavioral evidence. Conversely, computational trust models from multi-agent systems provide algorithmic updating but lack grounding in conceptual models that capture strategic dependencies covering mixed motives of actors. This technical report bridges this gap by developing a computational trust model that extends game-theoretic foundations for strategic coopetition with dynamic trust evolution. Building on companion work that achieved 58/60 validation (96.7%) for logarithmic specifications, we introduce trust as a two-layer system with immediate trust responding to current behavior and reputation tracking violation history. Trust evolves through asymmetric updating where cooperation builds trust gradually while violations erode it sharply, creating hysteresis effects and trust ceilings that constrain relationship recovery. We develop a structured translation framework enabling practitioners to instantiate computational trust models from i* dependency networks encompassing mixed motives of actors. Comprehensive experimental validation across 78,125 parameter configurations establishes robust emergence of negativity bias, hysteresis effects, and cumulative damage amplification. Empirical validation using the Renault-Nissan Alliance case study (1999-2025) achieves 49/60 validation points (81.7%), successfully reproducing documented trust evolution across five distinct relationship phases including crisis and recovery periods.

In the modern era of automation and robotics, autonomous vehicles are currently the focus of academic and industrial research. With the ever increasing number of unmanned aerial vehicles getting involved in activities in the civilian and commercial domain, there is an increased need for autonomy in these systems too. Due to guidelines set by the governments regarding the operation ceiling of civil drones, road-tracking based navigation is garnering interest . In an attempt to achieve the above mentioned tasks, we propose an imitation learning based, data-driven solution to UAV autonomy for navigating through city streets by learning to fly by imitating an expert pilot. Derived from the classic image classification algorithms, our classifier has been constructed in the form of a fast 39-layered Inception model, that evaluates the presence of roads using the tomographic reconstructions of the input frames. Based on the Inception-v3 architecture, our system performs better in terms of processing complexity and accuracy than many existing models for imitation learning. The data used for training the system has been captured from the drone, by flying it in and around urban and semi-urban streets, by experts having at least 6-8 years of flying experience. Permissions were taken from required authorities who made sure that minimal risk (to pedestrians) is involved in the data collection process. With the extensive amount of drone data that we collected, we have been able to navigate successfully through roads without crashing or overshooting, with an accuracy of 98.44%. The computational efficiency of MAVNet enables the drone to fly at high speeds of upto 6m/sec. We present the same results in this research and compare them with other state-of-the-art methods of vision and learning based navigation.

Computational notebooks such as Jupyter Notebook have become data scientists' de facto programming environments. Many visualization researchers and practitioners have developed interactive visualization tools that support notebooks. However, little is known about the appropriate design of visual analytics (VA) tools in notebooks. To bridge this critical research gap, we investigate the design strategies in this space by analyzing 159 notebook VA tools and their users' feedback. Our analysis encompasses 62 systems from academic papers and 103 systems sourced from a pool of 55k notebooks containing interactive visualizations that we obtain via scraping 8.6 million notebooks on GitHub. We also examine findings from 15 user studies and user feedback in 379 GitHub issues. Through this work, we identify unique design opportunities and considerations for future notebook VA tools, such as using and manipulating multimodal data in notebooks as well as balancing the degree of visualization-notebook integration. Finally, we develop SuperNOVA, an open-source interactive tool to help researchers explore existing notebook VA tools and search for related work.

Benchmarks play an important role in the development of machine learning algorithms. For example, research in reinforcement learning (RL) has been heavily influenced by available environments and benchmarks. However, RL environments are traditionally run on the CPU, limiting their scalability with typical academic compute. Recent advancements in JAX have enabled the wider use of hardware acceleration to overcome these computational hurdles, enabling massively parallel RL training pipelines and environments. This is particularly useful for multi-agent reinforcement learning (MARL) research. First of all, multiple agents must be considered at each environment step, adding computational burden, and secondly, the sample complexity is increased due to non-stationarity, decentralised partial observability, or other MARL challenges. In this paper, we present JaxMARL, the first open-source code base that combines ease-of-use with GPU enabled efficiency, and supports a large number of commonly used MARL environments as well as popular baseline algorithms. When considering wall clock time, our experiments show that per-run our JAX-based training pipeline is up to 12500x faster than existing approaches. This enables efficient and thorough evaluations, with the potential to alleviate the evaluation crisis of the field. We also introduce and benchmark SMAX, a vectorised, simplified version of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. We provide code at https://github.com/flairox/jaxmarl.

The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to scalability and data security, there is a growing shift towards decentralized systems for deploying such models. In these decentralized environments, efficient inference acceleration becomes crucial to manage computational resources effectively and enhance system responsiveness. In this work, we address the challenge of selecting optimal acceleration methods in decentralized systems by introducing a meta-learning-based framework. This framework automates the selection process by learning from historical performance data of various acceleration techniques across different tasks. Unlike traditional methods that rely on random selection or expert intuition, our approach systematically identifies the best acceleration strategies based on the specific characteristics of each task. We demonstrate that our meta-learning framework not only streamlines the decision-making process but also consistently outperforms conventional methods in terms of efficiency and performance. Our results highlight the potential of meta-learning to revolutionize inference acceleration in decentralized AI systems, offering a path towards more democratic and economically feasible artificial intelligence solutions.

Simultaneous Localization and Mapping (SLAM) is pivotal in robotics, with photorealistic scene reconstruction emerging as a key challenge. To address this, we introduce Computational Alignment for Real-Time Gaussian Splatting SLAM (CaRtGS), a novel method enhancing the efficiency and quality of photorealistic scene reconstruction in real-time environments. Leveraging 3D Gaussian Splatting (3DGS), CaRtGS achieves superior rendering quality and processing speed, which is crucial for scene photorealistic reconstruction. Our approach tackles computational misalignment in Gaussian Splatting SLAM (GS-SLAM) through an adaptive strategy that optimizes training, addresses long-tail optimization, and refines densification. Experiments on Replica and TUM-RGBD datasets demonstrate CaRtGS's effectiveness in achieving high-fidelity rendering with fewer Gaussian primitives. This work propels SLAM towards real-time, photorealistic dense rendering, significantly advancing photorealistic scene representation. For the benefit of the research community, we release the code on our project website: https://dapengfeng.github.io/cartgs.

Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states. To address this, we propose ProAct, a framework that enables agents to internalize accurate lookahead reasoning through a two-stage training paradigm. First, we introduce Grounded LookAhead Distillation (GLAD), where the agent undergoes supervised fine-tuning on trajectories derived from environment-based search. By compressing complex search trees into concise, causal reasoning chains, the agent learns the logic of foresight without the computational overhead of inference-time search. Second, to further refine decision accuracy, we propose the Monte-Carlo Critic (MC-Critic), a plug-and-play auxiliary value estimator designed to enhance policy-gradient algorithms like PPO and GRPO. By leveraging lightweight environment rollouts to calibrate value estimates, MC-Critic provides a low-variance signal that facilitates stable policy optimization without relying on expensive model-based value approximation. Experiments on both stochastic (e.g., 2048) and deterministic (e.g., Sokoban) environments demonstrate that ProAct significantly improves planning accuracy. Notably, a 4B parameter model trained with ProAct outperforms all open-source baselines and rivals state-of-the-art closed-source models, while demonstrating robust generalization to unseen environments. The codes and models are available at https://github.com/GreatX3/ProAct

High-resolution Vision-Language Models (VLMs) have been widely used in multimodal tasks to enhance accuracy by preserving detailed image information. However, these models often generate excessive visual tokens due to encoding multiple partitions of the input image. Processing these excessive visual tokens is computationally challenging, especially in resource-constrained environments with commodity GPUs. To support high-resolution images while meeting resource constraints, we propose High-Resolution Early Dropping (HiRED), a token-dropping scheme that operates within a fixed token budget before the Large Language Model (LLM) stage. HiRED can be integrated with existing high-resolution VLMs in a plug-and-play manner, as it requires no additional training while still maintaining superior accuracy. We strategically use the vision encoder's attention in the initial layers to assess the visual content of each image partition and allocate the token budget accordingly. Then, using the attention in the final layer, we select the most important visual tokens from each partition within the allocated budget, dropping the rest. Empirically, when applied to LLaVA-Next-7B on NVIDIA TESLA P40 GPU, HiRED with a 20% token budget increases token generation throughput by 4.7, reduces first-token generation latency by 15 seconds, and saves 2.3 GB of GPU memory for a single inference.

Recent advances in vision-language models (VLMs) have enabled powerful multimodal reasoning, but state-of-the-art approaches typically rely on extremely large models with prohibitive computational and memory requirements. This makes their deployment challenging in resource-constrained environments such as warehouses, robotics, and industrial applications, where both efficiency and robust spatial understanding are critical. In this work, we present SmolRGPT, a compact vision-language architecture that explicitly incorporates region-level spatial reasoning by integrating both RGB and depth cues. SmolRGPT employs a three-stage curriculum that progressively align visual and language features, enables spatial relationship understanding, and adapts to task-specific datasets. We demonstrate that with only 600M parameters, SmolRGPT achieves competitive results on challenging warehouse spatial reasoning benchmarks, matching or exceeding the performance of much larger alternatives. These findings highlight the potential for efficient, deployable multimodal intelligence in real-world settings without sacrificing core spatial reasoning capabilities. The code of the experimentation will be available at: https://github.com/abtraore/SmolRGPT

The capability of autonomous exploration in complex, unknown environments is important in many robotic applications. While recent research on autonomous exploration have achieved much progress, there are still limitations, e.g., existing methods relying on greedy heuristics or optimal path planning are often hindered by repetitive paths and high computational demands. To address such limitations, we propose a novel exploration framework that utilizes the global topology information of observed environment to improve exploration efficiency while reducing computational overhead. Specifically, global information is utilized based on a skeletal topological graph representation of the environment geometry. We first propose an incremental skeleton extraction method based on wavefront propagation, based on which we then design an approach to generate a lightweight topological graph that can effectively capture the environment's structural characteristics. Building upon this, we introduce a finite state machine that leverages the topological structure to efficiently plan coverage paths, which can substantially mitigate the back-and-forth maneuvers (BFMs) problem. Experimental results demonstrate the superiority of our method in comparison with state-of-the-art methods. The source code will be made publicly available at: https://github.com/Haochen-Niu/STGPlanner.

Crop detection is integral for precision agriculture applications such as automated yield estimation or fruit picking. However, crop detection, e.g., apple detection in orchard environments remains challenging due to a lack of large-scale datasets and the small relative size of the crops in the image. In this work, we address these challenges by reformulating the apple detection task in a semi-supervised manner. To this end, we provide the large, high-resolution dataset MAD comprising 105 labeled images with 14,667 annotated apple instances and 4,440 unlabeled images. Utilizing this dataset, we also propose a novel Semi-Supervised Small Apple Detection system S^3AD based on contextual attention and selective tiling to improve the challenging detection of small apples, while limiting the computational overhead. We conduct an extensive evaluation on MAD and the MSU dataset, showing that S^3AD substantially outperforms strong fully-supervised baselines, including several small object detection systems, by up to 14.9%. Additionally, we exploit the detailed annotations of our dataset w.r.t. apple properties to analyze the influence of relative size or level of occlusion on the results of various systems, quantifying current challenges.

Interest in applying Artificial Intelligence (AI) techniques to compiler optimizations is increasing rapidly, but compiler research has a high entry barrier. Unlike in other domains, compiler and AI researchers do not have access to the datasets and frameworks that enable fast iteration and development of ideas, and getting started requires a significant engineering investment. What is needed is an easy, reusable experimental infrastructure for real world compiler optimization tasks that can serve as a common benchmark for comparing techniques, and as a platform to accelerate progress in the field. We introduce CompilerGym, a set of environments for real world compiler optimization tasks, and a toolkit for exposing new optimization tasks to compiler researchers. CompilerGym enables anyone to experiment on production compiler optimization problems through an easy-to-use package, regardless of their experience with compilers. We build upon the popular OpenAI Gym interface enabling researchers to interact with compilers using Python and a familiar API. We describe the CompilerGym architecture and implementation, characterize the optimization spaces and computational efficiencies of three included compiler environments, and provide extensive empirical evaluations. Compared to prior works, CompilerGym offers larger datasets and optimization spaces, is 27x more computationally efficient, is fault-tolerant, and capable of detecting reproducibility bugs in the underlying compilers. In making it easy for anyone to experiment with compilers - irrespective of their background - we aim to accelerate progress in the AI and compiler research domains.

Quantum computing offers new ways to explore the theory of computation via the laws of quantum mechanics. Due to the rising demand for quantum computing resources, there is growing interest in developing cloud-based quantum resource sharing platforms that enable researchers to test and execute their algorithms on real quantum hardware. These cloud-based systems face a fundamental challenge in efficiently allocating quantum hardware resources to fulfill the growing computational demand of modern Internet of Things (IoT) applications. So far, attempts have been made in order to make efficient resource allocation, ranging from heuristic-based solutions to machine learning. In this work, we employ quantum reinforcement learning based on parameterized quantum circuits to address the resource allocation problem to support large IoT networks. We propose a python-based toolkit called QAISim for the simulation and modeling of Quantum Artificial Intelligence (QAI) models for designing resource management policies in quantum cloud environments. We have simulated policy gradient and Deep Q-Learning algorithms for reinforcement learning. QAISim exhibits a substantial reduction in model complexity compared to its classical counterparts with fewer trainable variables.

With the rapid evolution of Large Language Models (LLMs) and their large-scale experimentation in cloud-computing spaces, the challenge of guaranteeing their security and efficiency in a failure scenario has become a main issue. To ensure the reliability and availability of large-scale language models in cloud computing scenarios, such as frequent resource failures, network problems, and computational overheads, this study proposes a novel adaptive fault tolerance mechanism. It builds upon known fault-tolerant mechanisms, such as checkpointing, redundancy, and state transposition, introducing dynamic resource allocation and prediction of failure based on real-time performance metrics. The hybrid model integrates data driven deep learning-based anomaly detection technique underlining the contribution of cloud orchestration middleware for predictive prevention of system failures. Additionally, the model integrates adaptive checkpointing and recovery strategies that dynamically adapt according to load and system state to minimize the influence on the performance of the model and minimize downtime. The experimental results demonstrate that the designed model considerably enhances the fault tolerance in large-scale cloud surroundings, and decreases the system downtime by 30%, and has a better modeling availability than the classical fault tolerance mechanism.

The increasing deployment of autonomous systems in complex environments necessitates efficient communication and task completion among multiple agents. This paper presents SERN (Simulation-Enhanced Realistic Navigation), a novel framework integrating virtual and physical environments for real-time collaborative decision-making in multi-robot systems. SERN addresses key challenges in asset deployment and coordination through our bi-directional SERN ROS Bridge communication framework. Our approach advances the SOTA through: accurate real-world representation in virtual environments using Unity high-fidelity simulator; synchronization of physical and virtual robot movements; efficient ROS data distribution between remote locations; and integration of SOTA semantic segmentation for enhanced environmental perception. Additionally, we introduce a Multi-Metric Cost Function (MMCF) that dynamically balances latency, reliability, computational overhead, and bandwidth consumption to optimize system performance in contested environments. We further provide theoretical justification for synchronization accuracy by proving that the positional error between physical and virtual robots remains bounded under varying network conditions. Our evaluations show a 15% to 24% improvement in latency and up to a 15% increase in processing efficiency compared to traditional ROS setups. Real-world and virtual simulation experiments with multiple robots (Clearpath Jackal and Husky) demonstrate synchronization accuracy, achieving less than 5 cm positional error and under 2^circ rotational error. These results highlight SERN's potential to enhance situational awareness and multi-agent coordination in diverse, contested environments.

We introduce Shakti, a 2.5 billion parameter language model specifically optimized for resource-constrained environments such as edge devices, including smartphones, wearables, and IoT systems. Shakti combines high-performance NLP with optimized efficiency and precision, making it ideal for real-time AI applications where computational resources and memory are limited. With support for vernacular languages and domain-specific tasks, Shakti excels in industries such as healthcare, finance, and customer service. Benchmark evaluations demonstrate that Shakti performs competitively against larger models while maintaining low latency and on-device efficiency, positioning it as a leading solution for edge AI.

This study conducts a detailed comparison of RF-DETR object detection base model and YOLOv12 object detection model configurations for detecting greenfruits in a complex orchard environment marked by label ambiguity, occlusions, and background blending. A custom dataset was developed featuring both single-class (greenfruit) and multi-class (occluded and non-occluded greenfruits) annotations to assess model performance under dynamic real-world conditions. RF-DETR object detection model, utilizing a DINOv2 backbone and deformable attention, excelled in global context modeling, effectively identifying partially occluded or ambiguous greenfruits. In contrast, YOLOv12 leveraged CNN-based attention for enhanced local feature extraction, optimizing it for computational efficiency and edge deployment. RF-DETR achieved the highest mean Average Precision (mAP50) of 0.9464 in single-class detection, proving its superior ability to localize greenfruits in cluttered scenes. Although YOLOv12N recorded the highest mAP@50:95 of 0.7620, RF-DETR consistently outperformed in complex spatial scenarios. For multi-class detection, RF-DETR led with an mAP@50 of 0.8298, showing its capability to differentiate between occluded and non-occluded fruits, while YOLOv12L scored highest in mAP@50:95 with 0.6622, indicating better classification in detailed occlusion contexts. Training dynamics analysis highlighted RF-DETR's swift convergence, particularly in single-class settings where it plateaued within 10 epochs, demonstrating the efficiency of transformer-based architectures in adapting to dynamic visual data. These findings validate RF-DETR's effectiveness for precision agricultural applications, with YOLOv12 suited for fast-response scenarios. >Index Terms: RF-DETR object detection, YOLOv12, YOLOv13, YOLOv14, YOLOv15, YOLOE, YOLO World, YOLO, You Only Look Once, Roboflow, Detection Transformers, CNNs

This study systematically performed an extensive real-world evaluation of the performances of all configurations of YOLOv8, YOLOv9, YOLOv10, YOLO11( or YOLOv11), and YOLOv12 object detection algorithms in terms of precision, recall, mean Average Precision at 50\% Intersection over Union (mAP@50), and computational speeds including pre-processing, inference, and post-processing times immature green apple (or fruitlet) detection in commercial orchards. Additionally, this research performed and validated in-field counting of the fruitlets using an iPhone and machine vision sensors. Among the configurations, YOLOv12l recorded the highest recall rate at 0.90, compared to all other configurations of YOLO models. Likewise, YOLOv10x achieved the highest precision score of 0.908, while YOLOv9 Gelan-c attained a precision of 0.903. Analysis of mAP@0.50 revealed that YOLOv9 Gelan-base and YOLOv9 Gelan-e reached peak scores of 0.935, with YOLO11s and YOLOv12l following closely at 0.933 and 0.931, respectively. For counting validation using images captured with an iPhone 14 Pro, the YOLO11n configuration demonstrated outstanding accuracy, recording RMSE values of 4.51 for Honeycrisp, 4.59 for Cosmic Crisp, 4.83 for Scilate, and 4.96 for Scifresh; corresponding MAE values were 4.07, 3.98, 7.73, and 3.85. Similar performance trends were observed with RGB-D sensor data. Moreover, sensor-specific training on Intel Realsense data significantly enhanced model performance. YOLOv11n achieved highest inference speed of 2.4 ms, outperforming YOLOv8n (4.1 ms), YOLOv9 Gelan-s (11.5 ms), YOLOv10n (5.5 ms), and YOLOv12n (4.6 ms), underscoring its suitability for real-time object detection applications. (YOLOv12 architecture, YOLOv11 Architecture, YOLOv12 object detection, YOLOv11 object detecion, YOLOv12 segmentation)

This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA Hopper GPUs for large language model (LLM) inference tasks. We benchmark the overhead introduced by TEE mode across various LLMs and token lengths, with a particular focus on the bottleneck caused by CPU-GPU data transfers via PCIe. Our results indicate that while there is minimal computational overhead within the GPU, the overall performance penalty is primarily attributable to data transfer. For the majority of typical LLM queries, the overhead remains below 7%, with larger models and longer sequences experiencing nearly zero overhead.

Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-purpose capabilities for adapting to diverse scenarios and tasks. Real-time strategy (RTS) games serve as an ideal testbed for evaluating these two capabilities, as their inherent gameplay requires both macro-level strategic planning and micro-level tactical adaptation and action execution. Existing RTS game-based environments either suffer from relatively high computational demands or lack support for textual observations, which has constrained the use of RTS games for LLM evaluation. Motivated by this, we present TowerMind, a novel environment grounded in the tower defense (TD) subgenre of RTS games. TowerMind preserves the key evaluation strengths of RTS games for assessing LLMs, while featuring low computational demands and a multimodal observation space, including pixel-based, textual, and structured game-state representations. In addition, TowerMind supports the evaluation of model hallucination and provides a high degree of customizability. We design five benchmark levels to evaluate several widely used LLMs under different multimodal input settings. The results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions. The experiments further highlight key limitations in LLM behavior, such as inadequate planning validation, a lack of multifinality in decision-making, and inefficient action use. We also evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight and multimodal design, TowerMind complements the existing RTS game-based environment landscape and introduces a new benchmark for the AI agent field. The source code is publicly available on GitHub(https://github.com/tb6147877/TowerMind).

Accurate localization is an essential technology for the flexible navigation of robots in large-scale environments. Both SLAM-based and map-based localization will increase the computing load due to the increase in map size, which will affect downstream tasks such as robot navigation and services. To this end, we propose a localization system based on Block Maps (BMs) to reduce the computational load caused by maintaining large-scale maps. Firstly, we introduce a method for generating block maps and the corresponding switching strategies, ensuring that the robot can estimate the state in large-scale environments by loading local map information. Secondly, global localization according to Branch-and-Bound Search (BBS) in the 3D map is introduced to provide the initial pose. Finally, a graph-based optimization method is adopted with a dynamic sliding window that determines what factors are being marginalized whether a robot is exposed to a BM or switching to another one, which maintains the accuracy and efficiency of pose tracking. Comparison experiments are performed on publicly available large-scale datasets. Results show that the proposed method can track the robot pose even though the map scale reaches more than 6 kilometers, while efficient and accurate localization is still guaranteed on NCLT and M2DGR.

A computational ethics framework is essential for AI and autonomous systems operating in complex, real-world environments. Existing approaches often lack the adaptability needed to integrate ethical principles into dynamic and ambiguous contexts, limiting their effectiveness across diverse scenarios. To address these challenges, we outline the necessary ingredients for building a holistic, meta-level framework that combines intermediate representations, probabilistic reasoning, and knowledge representation. The specifications therein emphasize scalability, supporting ethical reasoning at both individual decision-making levels and within the collective dynamics of multi-agent systems. By integrating theoretical principles with contextual factors, it facilitates structured and context-aware decision-making, ensuring alignment with overarching ethical standards. We further explore proposed theorems outlining how ethical reasoners should operate, offering a foundation for practical implementation. These constructs aim to support the development of robust and ethically reliable AI systems capable of navigating the complexities of real-world moral decision-making scenarios.

Cyber-physical-social systems (CPSSs) have emerged in many applications over recent decades, requiring increased attention to security concerns. The rise of sophisticated threats like Advanced Persistent Threats (APTs) makes ensuring security in CPSSs particularly challenging. Provenance graph analysis has proven effective for tracing and detecting anomalies within systems, but the sheer size and complexity of these graphs hinder the efficiency of existing methods, especially those relying on graph neural networks (GNNs). To address these challenges, we present GraphDART, a modular framework designed to distill provenance graphs into compact yet informative representations, enabling scalable and effective anomaly detection. GraphDART can take advantage of diverse graph distillation techniques, including classic and modern graph distillation methods, to condense large provenance graphs while preserving essential structural and contextual information. This approach significantly reduces computational overhead, allowing GNNs to learn from distilled graphs efficiently and enhance detection performance. Extensive evaluations on benchmark datasets demonstrate the robustness of GraphDART in detecting malicious activities across cyber-physical-social systems. By optimizing computational efficiency, GraphDART provides a scalable and practical solution to safeguard interconnected environments against APTs.

As computational work becomes more and more integral to many aspects of scientific research, computational reproducibility has become an issue of increasing importance to computer systems researchers and domain scientists alike. Though computational reproducibility seems more straight forward than replicating physical experiments, the complex and rapidly changing nature of computer environments makes being able to reproduce and extend such work a serious challenge. In this paper, I explore common reasons that code developed for one research project cannot be successfully executed or extended by subsequent researchers. I review current approaches to these issues, including virtual machines and workflow systems, and their limitations. I then examine how the popular emerging technology Docker combines several areas from systems research - such as operating system virtualization, cross-platform portability, modular re-usable elements, versioning, and a `DevOps' philosophy, to address these challenges. I illustrate this with several examples of Docker use with a focus on the R statistical environment.

The increasing computational and memory demands in deep learning present significant challenges, especially in resource-constrained environments. We introduce a zero-order quantized optimization (ZOQO) method designed for training models with quantized parameters and operations. Our approach leverages zero-order approximations of the gradient sign and adapts the learning process to maintain the parameters' quantization without the need for full-precision gradient calculations. We demonstrate the effectiveness of ZOQO through experiments in fine-tuning of large language models and black-box adversarial attacks. Despite the limitations of zero-order and quantized operations training, our method achieves competitive performance compared to full-precision methods, highlighting its potential for low-resource environments.

We introduce AInsteinBench, a large-scale benchmark for evaluating whether large language model (LLM) agents can operate as scientific computing development agents within real research software ecosystems. Unlike existing scientific reasoning benchmarks which focus on conceptual knowledge, or software engineering benchmarks that emphasize generic feature implementation and issue resolving, AInsteinBench evaluates models in end-to-end scientific development settings grounded in production-grade scientific repositories. The benchmark consists of tasks derived from maintainer-authored pull requests across six widely used scientific codebases, spanning quantum chemistry, quantum computing, molecular dynamics, numerical relativity, fluid dynamics, and cheminformatics. All benchmark tasks are carefully curated through multi-stage filtering and expert review to ensure scientific challenge, adequate test coverage, and well-calibrated difficulty. By leveraging evaluation in executable environments, scientifically meaningful failure modes, and test-driven verification, AInsteinBench measures a model's ability to move beyond surface-level code generation toward the core competencies required for computational scientific research.

In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leveraging a unique mesh representation, RoMe ensures that the reconstructed road surfaces are accurate and seamlessly aligned with semantics. To address challenges in computational efficiency, we propose a waypoint sampling strategy, enabling RoMe to reconstruct vast environments by focusing on sub-areas and subsequently merging them. Furthermore, we incorporate an extrinsic optimization module to enhance the robustness against inaccuracies in extrinsic calibration. Our extensive evaluations of both public datasets and wild data underscore RoMe's superiority in terms of speed, accuracy, and robustness. For instance, it costs only 2 GPU hours to recover a road surface of 600*600 square meters from thousands of images. Notably, RoMe's capability extends beyond mere reconstruction, offering significant value for auto-labeling tasks in autonomous driving applications. All related data and code are available at https://github.com/DRosemei/RoMe.

Zero-Shot Object Navigation in unknown environments poses significant challenges for Unmanned Aerial Vehicles (UAVs) due to the conflict between high-level semantic reasoning requirements and limited onboard computational resources. To address this, we present USS-Nav, a lightweight framework that incrementally constructs a Unified Spatio-Semantic scene graph and enables efficient Large Language Model (LLM)-augmented Zero-Shot Object Navigation in unknown environments. Specifically, we introduce an incremental Spatial Connectivity Graph generation method utilizing polyhedral expansion to capture global geometric topology, which is dynamically partitioned into semantic regions via graph clustering. Concurrently, open-vocabulary object semantics are instantiated and anchored to this topology to form a hierarchical environmental representation. Leveraging this hierarchical structure, we present a coarse-to-fine exploration strategy: LLM grounded in the scene graph's semantics to determine global target regions, while a local planner optimizes frontier coverage based on information gain. Experimental results demonstrate that our framework outperforms state-of-the-art methods in terms of computational efficiency and real-time update frequency (15 Hz) on a resource-constrained platform. Furthermore, ablation studies confirm the effectiveness of our framework, showing substantial improvements in Success weighted by Path Length (SPL). The source code will be made publicly available to foster further research.

This paper presents Tiny-toxic-detector, a compact transformer-based model designed for toxic content detection. Despite having only 2.1 million parameters, Tiny-toxic-detector achieves competitive performance on benchmark datasets, with 90.97% accuracy on ToxiGen and 86.98% accuracy on the Jigsaw dataset, rivaling models over 50 times its size. This efficiency enables deployment in resource-constrained environments, addressing the need for effective content moderation tools that balance performance with computational efficiency. The model architecture features 4 transformer encoder layers, each with 2 attention heads, an embedding dimension of 64, and a feedforward dimension of 128. Trained on both public and private datasets, Tiny-toxic-detector demonstrates the potential of efficient, task-specific models for addressing online toxicity. The paper covers the model architecture, training process, performance benchmarks, and limitations, underscoring its suitability for applications such as social media monitoring and content moderation. By achieving results comparable to much larger models while significantly reducing computational demands, Tiny-toxic-detector represents progress toward more sustainable and scalable AI-driven content moderation solutions.

The growing demand for Large Language Models (LLMs) across diverse applications has prompted a paradigm shift in the design of deep learning serving systems. Deploying LLMs, especially in multi-tenant environments, presents considerable challenges due to their high computational and memory demands. We present BlockLLM, a serving system that exploits the potential of sharing components among fine-tuned LLM models to offer an efficient and flexible solution for LLM workloads. BlockLLM partitions the models into finer-grained blocks to enable the reuse of model components and independent provisioning to improve the computation efficiency. BlockLLM consists of an offline block zoo, for storing the blocks, and an online system to serve the requests through chains of blocks. It offers multi-fold flexibility: (1) Adaptive assembly of block chains on-the-fly is achieved with the help of equivalence evaluation among blocks in the zoo. (2) We enable per-block batch size and configure best-effort KV cache coordination at individual block level. (3) We adopt speculative execution and locality-aware block placement to mitigate the communication costs from dynamic block resource allocation. Our evaluation demonstrates that BlockLLM reduces memory and storage footprints and improves computation efficiency, outperforming existing serving approach in 95\%ile latency and GPU utilization by 33.5\% and 20.1\%, respectively.

Large language models (LLMs) have shown remarkable performance in various natural language processing tasks. However, a primary constraint they face is the context limit, i.e., the maximum number of tokens they can process. Previous works have explored architectural changes and modifications in positional encoding to relax the constraint, but they often require expensive training or do not address the computational demands of self-attention. In this paper, we present Hierarchical cOntext MERging (HOMER), a new training-free scheme designed to overcome the limitations. HOMER uses a divide-and-conquer algorithm, dividing long inputs into manageable chunks. Each chunk is then processed collectively, employing a hierarchical strategy that merges adjacent chunks at progressive transformer layers. A token reduction technique precedes each merging, ensuring memory usage efficiency. We also propose an optimized computational order reducing the memory requirement to logarithmically scale with respect to input length, making it especially favorable for environments with tight memory restrictions. Our experiments demonstrate the proposed method's superior performance and memory efficiency, enabling the broader use of LLMs in contexts requiring extended context. Code is available at https://github.com/alinlab/HOMER.

The Segment Anything Model (SAM) has set a new standard in interactive image segmentation, offering robust performance across various tasks. However, its significant computational requirements limit its deployment in real-time or resource-constrained environments. To address these challenges, we propose a novel knowledge distillation approach, KD SAM, which incorporates both encoder and decoder optimization through a combination of Mean Squared Error (MSE) and Perceptual Loss. This dual-loss framework captures structural and semantic features, enabling the student model to maintain high segmentation accuracy while reducing computational complexity. Based on the model evaluation on datasets, including Kvasir-SEG, ISIC 2017, Fetal Head Ultrasound, and Breast Ultrasound, we demonstrate that KD SAM achieves comparable or superior performance to the baseline models, with significantly fewer parameters. KD SAM effectively balances segmentation accuracy and computational efficiency, making it well-suited for real-time medical image segmentation applications in resource-constrained environments.

Humans rapidly learn abstract knowledge when encountering novel environments and flexibly deploy this knowledge to guide efficient and intelligent action. Can modern AI systems learn and plan in a similar way? We study this question using a dataset of complex human gameplay with concurrent fMRI recordings, in which participants learn novel video games that require rule discovery, hypothesis revision, and multi-step planning. We jointly evaluate models by their ability to play the games, match human learning behavior, and predict brain activity during the same task, comparing a suite of frontier Large Reasoning Models (LRMs) against model-free and model-based deep reinforcement learning agents and a Bayesian theory-based agent. We find that frontier LRMs most closely match human behavioral patterns during game discovery and predict brain activity an order of magnitude better than both reinforcement learning alternatives across cortical and subcortical regions, with effects robust to permutation controls. Through targeted manipulations, we further show that brain alignment reflects the model's in-context representation of the game state rather than its downstream planning or reasoning. Our results establish LRMs as compelling computational accounts of human learning and decision making in complex, naturalistic environments. Project page with interactive replays: https://botcs.github.io/reason-to-play/

Convolutional Neural Networks (CNNs) are pivotal in image classification tasks due to their robust feature extraction capabilities. However, their high computational and memory requirements pose challenges for deployment in resource-constrained environments. This paper introduces a methodology to construct lightweight CNNs while maintaining competitive accuracy. The approach integrates two stages of training; dual-input-output model and transfer learning with progressive unfreezing. The dual-input-output model train on original and augmented datasets, enhancing robustness. Progressive unfreezing is applied to the unified model to optimize pre-learned features during fine-tuning, enabling faster convergence and improved model accuracy. The methodology was evaluated on three benchmark datasets; handwritten digit MNIST, fashion MNIST, and CIFAR-10. The proposed model achieved a state-of-the-art accuracy of 99% on the handwritten digit MNIST and 89% on fashion MNIST, with only 14,862 parameters and a model size of 0.17 MB. While performance on CIFAR-10 was comparatively lower (65% with less than 20,00 parameters), the results highlight the scalability of this method. The final model demonstrated fast inference times and low latency, making it suitable for real-time applications. Future directions include exploring advanced augmentation techniques, improving architectural scalability for complex datasets, and extending the methodology to tasks beyond classification. This research underscores the potential for creating efficient, scalable, and task-specific CNNs for diverse applications.

Current robots are either expensive or make significant compromises on sensory richness, computational power, and communication capabilities. We propose to leverage smartphones to equip robots with extensive sensor suites, powerful computational abilities, state-of-the-art communication channels, and access to a thriving software ecosystem. We design a small electric vehicle that costs $50 and serves as a robot body for standard Android smartphones. We develop a software stack that allows smartphones to use this body for mobile operation and demonstrate that the system is sufficiently powerful to support advanced robotics workloads such as person following and real-time autonomous navigation in unstructured environments. Controlled experiments demonstrate that the presented approach is robust across different smartphones and robot bodies. A video of our work is available at https://www.youtube.com/watch?v=qc8hFLyWDOM

Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where models favor extended internal reasoning chains over environmental interaction. Through experiments on software engineering tasks using SWE Bench Verified, we observe three recurring patterns: Analysis Paralysis, Rogue Actions, and Premature Disengagement. We propose a framework to study these behaviors, which correlates with human expert assessments, and analyze 4018 trajectories. We observe that higher overthinking scores correlate with decreased performance, with reasoning models exhibiting stronger tendencies toward overthinking compared to non-reasoning models. Our analysis reveals that simple efforts to mitigate overthinking in agentic environments, such as selecting the solution with the lower overthinking score, can improve model performance by almost 30% while reducing computational costs by 43%. These results suggest that mitigating overthinking has strong practical implications. We suggest that by leveraging native function-calling capabilities and selective reinforcement learning overthinking tendencies could be mitigated. We also open-source our evaluation framework and dataset to facilitate research in this direction at https://github.com/AlexCuadron/Overthinking.

LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

This paper presents a vision-only autonomous flight system for small UAVs operating in controlled indoor environments. The system combines semantic segmentation with monocular depth estimation to enable obstacle avoidance, scene exploration, and autonomous safe landing operations without requiring GPS or expensive sensors such as LiDAR. A key innovation is an adaptive scale factor algorithm that converts non-metric monocular depth predictions into accurate metric distance measurements by leveraging semantic ground plane detection and camera intrinsic parameters, achieving a mean distance error of 14.4 cm. The approach uses a knowledge distillation framework where a color-based Support Vector Machine (SVM) teacher generates training data for a lightweight U-Net student network (1.6M parameters) capable of real-time semantic segmentation. For more complex environments, the SVM teacher can be replaced with a state-of-the-art segmentation model. Testing was conducted in a controlled 5x4 meter laboratory environment with eight cardboard obstacles simulating urban structures. Extensive validation across 30 flight tests in a real-world environment and 100 flight tests in a digital-twin environment demonstrates that the combined segmentation and depth approach increases the distance traveled during surveillance and reduces mission time while maintaining 100% success rates. The system is further optimized through end-to-end learning, where a compact student neural network learns complete flight policies from demonstration data generated by our best-performing method, achieving an 87.5% autonomous mission success rate. This work advances practical vision-based drone navigation in structured environments, demonstrating solutions for metric depth estimation and computational efficiency challenges that enable deployment on resource-constrained platforms.

Reliable long-range flight of unmanned aerial vehicles (UAVs) in GNSS-denied environments is challenging: integrating odometry leads to drift, loop closures are unavailable in previously unseen areas and embedded platforms provide limited computational power. We present a fully onboard UAV system developed for the SPRIN-D Funke Fully Autonomous Flight Challenge, which required 9 km long-range waypoint navigation below 25 m AGL (Above Ground Level) without GNSS or prior dense mapping. The system integrates perception, mapping, planning, and control with a lightweight drift-correction method that matches LiDAR-derived local heightmaps to a prior geo-data heightmap via gradient-template matching and fuses the evidence with odometry in a clustered particle filter. Deployed during the competition, the system executed kilometer-scale flights across urban, forest, and open-field terrain and reduced drift substantially relative to raw odometry, while running in real time on CPU-only hardware. We describe the system architecture, the localization pipeline, and the competition evaluation, and we report practical insights from field deployment that inform the design of GNSS-denied UAV autonomy.

Multi-agent collaborative perception is expected to significantly improve perception performance by overcoming the limitations of single-agent perception through exchanging complementary information. However, training a robust collaborative perception model requires collecting sufficient training data that covers all possible collaboration scenarios, which is impractical due to intolerable deployment costs. Hence, the trained model is not robust against new traffic scenarios with inconsistent data distribution and fundamentally restricts its real-world applicability. Further, existing methods, such as domain adaptation, have mitigated this issue by exposing the deployment data during the training stage but incur a high training cost, which is infeasible for resource-constrained agents. In this paper, we propose a Parameter-Efficient Fine-Tuning-based lightweight framework, CoPEFT, for fast adapting a trained collaborative perception model to new deployment environments under low-cost conditions. CoPEFT develops a Collaboration Adapter and Agent Prompt to perform macro-level and micro-level adaptations separately. Specifically, the Collaboration Adapter utilizes the inherent knowledge from training data and limited deployment data to adapt the feature map to new data distribution. The Agent Prompt further enhances the Collaboration Adapter by inserting fine-grained contextual information about the environment. Extensive experiments demonstrate that our CoPEFT surpasses existing methods with less than 1\% trainable parameters, proving the effectiveness and efficiency of our proposed method.

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward engineering and reward shaping in enhancing the efficiency and effectiveness of reinforcement learning algorithms. Reward engineering involves designing reward functions that accurately reflect the desired outcomes, while reward shaping provides additional feedback to guide the learning process, accelerating convergence to optimal policies. Despite significant advancements in reinforcement learning, several limitations persist. One key challenge is the sparse and delayed nature of rewards in many real-world scenarios, which can hinder learning progress. Additionally, the complexity of accurately modeling real-world environments and the computational demands of reinforcement learning algorithms remain substantial obstacles. On the other hand, recent advancements in deep learning and neural networks have significantly improved the capability of reinforcement learning systems to handle high-dimensional state and action spaces, enabling their application to complex tasks such as robotics, autonomous driving, and game playing. This paper provides a comprehensive review of the current state of reinforcement learning, focusing on the methodologies and techniques used in reward engineering and reward shaping. It critically analyzes the limitations and recent advancements in the field, offering insights into future research directions and potential applications in various domains.

Sunlight and shadow play critical roles in how urban spaces are utilized, thrive, and grow. While access to sunlight is essential to the success of urban environments, shadows can provide shaded places to stay during the hot seasons, mitigate heat island effect, and increase pedestrian comfort levels. Properly quantifying sunlight access and shadows in large urban environments is key in tackling some of the important challenges facing cities today. In this paper, we propose Deep Umbra, a novel computational framework that enables the quantification of sunlight access and shadows at a global scale. Our framework is based on a conditional generative adversarial network that considers the physical form of cities to compute high-resolution spatial information of accumulated sunlight access for the different seasons of the year. We use data from seven different cities to train our model, and show, through an extensive set of experiments, its low overall RMSE (below 0.1) as well as its extensibility to cities that were not part of the training set. Additionally, we contribute a set of case studies and a comprehensive dataset with sunlight access information for more than 100 cities across six continents of the world. Deep Umbra is available at https://urbantk.org/shadows.

This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in order to help AI agents rapidly learn. We show that such algorithms are possible via Generative Teaching Networks (GTNs), a general approach that is, in theory, applicable to supervised, unsupervised, and reinforcement learning, although our experiments only focus on the supervised case. GTNs are deep neural networks that generate data and/or training environments that a learner (e.g. a freshly initialized neural network) trains on for a few SGD steps before being tested on a target task. We then differentiate through the entire learning process via meta-gradients to update the GTN parameters to improve performance on the target task. GTNs have the beneficial property that they can theoretically generate any type of data or training environment, making their potential impact large. This paper introduces GTNs, discusses their potential, and showcases that they can substantially accelerate learning. We also demonstrate a practical and exciting application of GTNs: accelerating the evaluation of candidate architectures for neural architecture search (NAS), which is rate-limited by such evaluations, enabling massive speed-ups in NAS. GTN-NAS improves the NAS state of the art, finding higher performing architectures when controlling for the search proposal mechanism. GTN-NAS also is competitive with the overall state of the art approaches, which achieve top performance while using orders of magnitude less computation than typical NAS methods. Speculating forward, GTNs may represent a first step toward the ambitious goal of algorithms that generate their own training data and, in doing so, open a variety of interesting new research questions and directions.

Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for Reasoning (CLEAR). It performs rational abandonment and reallocates resources from insolvent queries to solvable queries near their emergence thresholds. Extensive experiments on several reasoning tasks with different traffic streams demonstrate that CLEAR significantly improves the Pareto frontier of total token cost versus mean accuracy. In resource-scarce regimes, CLEAR achieves up to a 3x improvement in global accuracy compared to uniform allocation.

Large language models (LLMs) achieve remarkable performance but demand substantial computational resources, limiting deployment on edge devices and resource-constrained environments. We present TernaryLM, a 132M parameter transformer architecture that employs native 1-bit ternary quantization {-1, 0, +1} during training, achieving significant memory reduction without sacrificing language modeling capability. Unlike post-training quantization approaches that quantize pre-trained full-precision models, TernaryLM learns quantization-aware representations from scratch using straight-through estimators and adaptive per-layer scaling factors. Our experiments demonstrate: (1) validation perplexity of 58.42 on TinyStories; (2) downstream transfer with 82.47 percent F1 on MRPC paraphrase detection; (3) 2.4x memory reduction (498MB vs 1197MB) with comparable inference latency; and (4) stable training dynamics across diverse corpora. We provide layer-wise quantization analysis showing that middle transformer layers exhibit highest compatibility with extreme quantization, informing future non-uniform precision strategies. Our results suggest that native 1-bit training is a promising direction for efficient neural language models. Code is available at https://github.com/1nisharg/TernaryLM-Memory-Efficient-Language-Modeling.

The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant computational and memory resources due to the necessity of recalculating and storing attention weights across different layers. This paper introduces a novel Shared Attention (SA) mechanism, designed to enhance the efficiency of LLMs by directly sharing computed attention weights across multiple layers. Unlike previous methods that focus on sharing intermediate Key-Value (KV) caches, our approach utilizes the isotropic tendencies of attention distributions observed in advanced LLMs post-pretraining to reduce both the computational flops and the size of the KV cache required during inference. We empirically demonstrate that implementing SA across various LLMs results in minimal accuracy loss on standard benchmarks. Our findings suggest that SA not only conserves computational resources but also maintains robust model performance, thereby facilitating the deployment of more efficient LLMs in resource-constrained environments.

Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit their deployment in resource-constrained environments. Low-rank approximation is an effective method for computer vision and natural language processing models, but its application in compressing CTR prediction models has been less explored. Due to the limited memory and computing resources, compression of CTR prediction models often confronts three fundamental challenges, i.e., (1). How to reduce the model sizes to adapt to edge devices? (2). How to speed up CTR prediction model inference? (3). How to retain the capabilities of original models after compression? Previous low-rank compression research mostly uses tensor decomposition, which can achieve a high parameter compression ratio, but brings in AUC degradation and additional computing overhead. To address these challenges, we propose a unified low-rank decomposition framework for compressing CTR prediction models. We find that even with the most classic matrix decomposition SVD method, our framework can achieve better performance than the original model. To further improve the effectiveness of our framework, we locally compress the output features instead of compressing the model weights. Our unified low-rank compression framework can be applied to embedding tables and MLP layers in various CTR prediction models. Extensive experiments on two academic datasets and one real industrial benchmark demonstrate that, with 3-5x model size reduction, our compressed models can achieve both faster inference and higher AUC than the uncompressed original models. Our code is at https://github.com/yuhao318/Atomic_Feature_Mimicking.

Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing. However, high computational and memory demands of state-of-the-art architectures pose challenges for deployment in resource-limited environments. Knowledge Distillation (KD) addresses this by transferring knowledge from a large teacher model to a smaller, more efficient student model while maintaining competitive performance. In this work, we investigate the effectiveness of KD for Time Series Classification (TSC) across three architectures: the classical Fully Convolutional Network (FCN), the convolutional Inception model and the transformer-based ConvTran model. We evaluate our approach on UCR Archive, the largest benchmark repository of time series datasets, by modifying architectural components such as convolutional filters, Inception modules and attention heads across the three architectures. Our results consistently show that KD most effectively benefits student models of intermediate complexity across all three architectures, with the distilled FCN student reducing parameters by a factor of 38, the distilled Inception student achieving nearly the same performance as the teacher with 42% fewer parameters and the distilled ConvTran student with 2 attention heads showing the most significant improvement through distillation. To encourage further research and reproducibility, we provide our implementation at https://github.com/MSD-IRIMAS/KD-4-TSC.

Large language models (LLMs) have demonstrated impressive capabilities in code generation by leveraging retrieval-augmented generation (RAG) methods. However, the computational costs associated with LLM inference, particularly in terms of latency and energy consumption, have received limited attention in the security context. This paper introduces DrainCode, the first adversarial attack targeting the computational efficiency of RAG-based code generation systems. By strategically poisoning retrieval contexts through a mutation-based approach, DrainCode forces LLMs to produce significantly longer outputs, thereby increasing GPU latency and energy consumption. We evaluate the effectiveness of DrainCode across multiple models. Our experiments show that DrainCode achieves up to an 85% increase in latency, a 49% increase in energy consumption, and more than a 3x increase in output length compared to the baseline. Furthermore, we demonstrate the generalizability of the attack across different prompting strategies and its effectiveness compared to different defenses. The results highlight DrainCode as a potential method for increasing the computational overhead of LLMs, making it useful for evaluating LLM security in resource-constrained environments. We provide code and data at https://github.com/DeepSoftwareAnalytics/DrainCode.

Many of society's most pressing challenges, from pandemic response to supply chain disruptions to climate adaptation, emerge from the collective behavior of millions of autonomous agents making decisions over time. Large Population Models (LPMs) offer an approach to understand these complex systems by simulating entire populations with realistic behaviors and interactions at unprecedented scale. LPMs extend traditional modeling approaches through three key innovations: computational methods that efficiently simulate millions of agents simultaneously, mathematical frameworks that learn from diverse real-world data streams, and privacy-preserving communication protocols that bridge virtual and physical environments. This allows researchers to observe how agent behavior aggregates into system-level outcomes and test interventions before real-world implementation. While current AI advances primarily focus on creating "digital humans" with sophisticated individual capabilities, LPMs develop "digital societies" where the richness of interactions reveals emergent phenomena. By bridging individual agent behavior and population-scale dynamics, LPMs offer a complementary path in AI research illuminating collective intelligence and providing testing grounds for policies and social innovations before real-world deployment. We discuss the technical foundations and some open problems here. LPMs are implemented by the AgentTorch framework (github.com/AgentTorch/AgentTorch)

Deep neural networks (DNNs) have remarkably succeeded in various image processing tasks. However, their large size and computational complexity present significant challenges for deploying them in resource-constrained environments. This paper presents an innovative approach for integrating Mamba Architecture within a Progressive Knowledge Distillation (PKD) process to address the challenge of reducing model complexity while maintaining accuracy in image classification tasks. The proposed framework distills a large teacher model into progressively smaller student models, designed using Mamba blocks. Each student model is trained using Selective-State-Space Models (S-SSM) within the Mamba blocks, focusing on important input aspects while reducing computational complexity. The work's preliminary experiments use MNIST and CIFAR-10 as datasets to demonstrate the effectiveness of this approach. For MNIST, the teacher model achieves 98% accuracy. A set of seven student models as a group retained 63% of the teacher's FLOPs, approximating the teacher's performance with 98% accuracy. The weak student used only 1% of the teacher's FLOPs and maintained 72% accuracy. Similarly, for CIFAR-10, the students achieved 1% less accuracy compared to the teacher, with the small student retaining 5% of the teacher's FLOPs to achieve 50% accuracy. These results confirm the flexibility and scalability of Mamba Architecture, which can be integrated into PKD, succeeding in the process of finding students as weak learners. The framework provides a solution for deploying complex neural networks in real-time applications with a reduction in computational cost.

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens processed, limiting their practicality in resource-constrained environments. We introduce Language-Guided Vision Token Pruning (LVPruning) for MLLMs, an effective yet simple method that significantly reduces the computational burden while preserving model performance. LVPruning employs cross-attention modules to compute the importance of vision tokens based on their interaction with language tokens, determining which to prune. Importantly, LVPruning can be integrated without modifying the original MLLM parameters, which makes LVPruning simple to apply or remove. Our experiments show that LVPruning can effectively reduce up to 90% of vision tokens by the middle layer of LLaVA-1.5, resulting in a 62.1% decrease in inference Tera Floating-Point Operations Per Second (TFLOPs), with an average performance loss of just 0.45% across nine multi-modal benchmarks.

The success of Large Language Models (LLM) has led researchers to explore Multimodal Large Language Models (MLLM) for unified visual and linguistic understanding. However, the increasing model size and computational complexity of MLLM limit their use in resource-constrained environments. Small-scale MLLM (s-MLLM) aims to retain the capabilities of the large-scale model (l-MLLM) while reducing computational demands, but resulting in a significant decline in performance. To address the aforementioned issues, we propose a novel LLaVA-KD framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM, and Relation Distillation (RDist) to transfer l-MLLM's ability to model correlations between visual features. Additionally, we propose a three-stage training scheme to fully exploit the potential of s-MLLM: 1) Distilled Pre-Training to align visual-textual representations, 2) Supervised Fine-Tuning to equip the model with multimodal understanding, and 3) Distilled Fine-Tuning to further transfer l-MLLM capabilities. Our approach significantly improves performance without altering the small model's architecture. Extensive experiments and ablation studies validate the effectiveness of each proposed component. Code will be available at https://github.com/caiyuxuan1120/LLaVA-KD.

Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. However, the high computational and memory demands of ViTs pose significant challenges for deployment in resource-constrained environments. This paper introduces ViT-1.58b, a novel 1.58-bit quantized ViT model designed to drastically reduce memory and computational overhead while preserving competitive performance. ViT-1.58b employs ternary quantization, which refines the balance between efficiency and accuracy by constraining weights to {-1, 0, 1} and quantizing activations to 8-bit precision. Our approach ensures efficient scaling in terms of both memory and computation. Experiments on CIFAR-10 and ImageNet-1k demonstrate that ViT-1.58b maintains comparable accuracy to full-precision Vit, with significant reductions in memory usage and computational costs. This paper highlights the potential of extreme quantization techniques in developing sustainable AI solutions and contributes to the broader discourse on efficient model deployment in practical applications. Our code and weights are available at https://github.com/DLYuanGod/ViT-1.58b.

Graph Transformers (GTs) have achieved impressive results on various graph-related tasks. However, the huge computational cost of GTs hinders their deployment and application, especially in resource-constrained environments. Therefore, in this paper, we explore the feasibility of sparsifying GTs, a significant yet under-explored topic. We first discuss the redundancy of GTs based on the characteristics of existing GT models, and then propose a comprehensive Graph Transformer SParsification (GTSP) framework that helps to reduce the computational complexity of GTs from four dimensions: the input graph data, attention heads, model layers, and model weights. Specifically, GTSP designs differentiable masks for each individual compressible component, enabling effective end-to-end pruning. We examine our GTSP through extensive experiments on prominent GTs, including GraphTrans, Graphormer, and GraphGPS. The experimental results substantiate that GTSP effectively cuts computational costs, accompanied by only marginal decreases in accuracy or, in some cases, even improvements. For instance, GTSP yields a reduction of 30\% in Floating Point Operations while contributing to a 1.8\% increase in Area Under the Curve accuracy on OGBG-HIV dataset. Furthermore, we provide several insights on the characteristics of attention heads and the behavior of attention mechanisms, all of which have immense potential to inspire future research endeavors in this domain.

Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel (3times3 or more). However, the heavy computational footprint of such models prevents their deployment in real-time, resource-constrained environments. Conversely, 1times1 convolutions bring substantial computational efficiency, but struggle with aggregating local spatial representations, an essential capability to SISR models. In response to this dichotomy, we propose to harmonize the merits of both 3times3 and 1times1 kernels, and exploit a great potential for lightweight SISR tasks. Specifically, we propose a simple yet effective fully 1times1 convolutional network, named Shift-Conv-based Network (SCNet). By incorporating a parameter-free spatial-shift operation, it equips the fully 1times1 convolutional network with powerful representation capability while impressive computational efficiency. Extensive experiments demonstrate that SCNets, despite its fully 1times1 convolutional structure, consistently matches or even surpasses the performance of existing lightweight SR models that employ regular convolutions.

The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement Learning, with more natural exploration capabilities. A promising approach in this respect has consisted of using Bayesian surprise on model parameters, i.e. a metric for the difference between prior and posterior beliefs, to favour exploration. In this contribution, we propose to apply Bayesian surprise in a latent space representing the agent's current understanding of the dynamics of the system, drastically reducing the computational costs. We extensively evaluate our method by measuring the agent's performance in terms of environment exploration, for continuous tasks, and looking at the game scores achieved, for video games. Our model is computationally cheap and compares positively with current state-of-the-art methods on several problems. We also investigate the effects caused by stochasticity in the environment, which is often a failure case for curiosity-driven agents. In this regime, the results suggest that our approach is resilient to stochastic transitions.

Streaming reconstruction from monocular image sequences remains challenging, as existing methods typically favor either high-quality rendering or accurate geometry, but rarely both. We present PLANING, an efficient on-the-fly reconstruction framework built on a hybrid representation that loosely couples explicit geometric primitives with neural Gaussians, enabling geometry and appearance to be modeled in a decoupled manner. This decoupling supports an online initialization and optimization strategy that separates geometry and appearance updates, yielding stable streaming reconstruction with substantially reduced structural redundancy. PLANING improves dense mesh Chamfer-L2 by 18.52% over PGSR, surpasses ARTDECO by 1.31 dB PSNR, and reconstructs ScanNetV2 scenes in under 100 seconds, over 5x faster than 2D Gaussian Splatting, while matching the quality of offline per-scene optimization. Beyond reconstruction quality, the structural clarity and computational efficiency of \modelname~make it well suited for a broad range of downstream applications, such as enabling large-scale scene modeling and simulation-ready environments for embodied AI. Project page: https://city-super.github.io/PLANING/ .

As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via fast-executing unit tests, MLE verification requires running full ML pipelines -- data preprocessing, model training, and metric evaluation -- on large datasets at each rollout step, rendering trajectory-wise on-policy reinforcement learning (RL) prohibitively slow. Existing approaches retreat to supervised fine-tuning (SFT) or offline proxy rewards, sacrificing the exploration and generalization benefits of on-policy RL. We observe that sandbox data size is the primary source of this bottleneck. Based on this insight, we introduce SandMLE, a multi-agent framework that generates diverse, verifiable synthetic MLE environments from a small number of seed tasks, preserving the structural and technical complexity of real-world problems while constraining datasets to micro-scale (each task is paired with only 50-200 training samples). Through extensive experiments, we show that SandMLE reduces execution time by over 13 times, enabling large-scale, on-policy trajectory-wise RL for the first time in the MLE domain. On MLE-bench-lite, SandMLE yields significant gains over SFT baselines across Qwen3-8B, 14B, and 30B-A3B, with relative medal rate improvements ranging from 20.3% to 66.9%. Furthermore, the trained policy generalizes across unseen agentic scaffolds, achieving up to 32.4% better HumanRank score on MLE-Dojo.

This work presents MAC-Flow, a simple yet expressive framework for multi-agent coordination. We argue that requirements of effective coordination are twofold: (i) a rich representation of the diverse joint behaviors present in offline data and (ii) the ability to act efficiently in real time. However, prior approaches often sacrifice one for the other, i.e., denoising diffusion-based solutions capture complex coordination but are computationally slow, while Gaussian policy-based solutions are fast but brittle in handling multi-agent interaction. MAC-Flow addresses this trade-off by first learning a flow-based representation of joint behaviors, and then distilling it into decentralized one-step policies that preserve coordination while enabling fast execution. Across four different benchmarks, including 12 environments and 34 datasets, MAC-Flow alleviates the trade-off between performance and computational cost, specifically achieving about times14.5 faster inference compared to diffusion-based MARL methods, while maintaining good performance. At the same time, its inference speed is similar to that of prior Gaussian policy-based offline multi-agent reinforcement learning (MARL) methods.

Large language models (LLMs) have demonstrated significant capabilities in natural language processing and reasoning, yet their effectiveness in autonomous planning has been under debate. While existing studies have utilized LLMs with external feedback mechanisms or in controlled environments for planning, these approaches often involve substantial computational and development resources due to the requirement for careful design and iterative backprompting. Moreover, even the most advanced LLMs like GPT-4 struggle to match human performance on standard planning benchmarks, such as the Blocksworld, without additional support. This paper investigates whether LLMs can independently generate long-horizon plans that rival human baselines. Our novel enhancements to Algorithm-of-Thoughts (AoT), which we dub AoT+, help achieve state-of-the-art results in planning benchmarks out-competing prior methods and human baselines all autonomously.

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed. We propose When2Tool, a benchmark of 18 environments (15 single-hop, 3 multi-hop) spanning three categories of tool necessity -- computational scale, knowledge boundaries, and execution reliability -- each with controlled difficulty levels that create a clear decision boundary between tool-necessary and tool-unnecessary tasks. We evaluate two families of training-free baselines: Prompt-only (varying the prompt to discourage unnecessary calls) and Reason-then-Act (requiring the model to reason about tool necessity before acting). Both provide limited control: Prompt-only suppresses necessary calls alongside unnecessary ones, and Reason-then-Act still incurs a disproportionate accuracy cost on hard tasks. To understand why these baselines fail, we probe the models' hidden states and find that tool necessity is linearly decodable from the pre-generation representation with AUROC 0.89--0.96 across six models, substantially exceeding the model's own verbalized reasoning. This reveals that models already know when tools are needed, but fail to act on this knowledge during generation. Building on this finding, we propose Probe&Prefill, which uses a lightweight linear probe to read the hidden-state signal and prefills the model's response with a steering sentence. Across all models tested, Probe&Prefill reduces tool calls by 48% with only 1.7% accuracy loss, while the best baseline at comparable accuracy only reduces 6% of tool calls, or achieves a similar tool call reduction but incurs a 5times higher accuracy loss. Our code is available at https://github.com/Trustworthy-ML-Lab/when2tool

The rapid evolution of malware attacks calls for the development of innovative detection methods, especially in resource-constrained edge computing. Traditional detection techniques struggle to keep up with modern malware's sophistication and adaptability, prompting a shift towards advanced methodologies like those leveraging Large Language Models (LLMs) for enhanced malware detection. However, deploying LLMs for malware detection directly at edge devices raises several challenges, including ensuring accuracy in constrained environments and addressing edge devices' energy and computational limits. To tackle these challenges, this paper proposes an architecture leveraging lightweight LLMs' strengths while addressing limitations like reduced accuracy and insufficient computational power. To evaluate the effectiveness of the proposed lightweight LLM-based approach for edge computing, we perform an extensive experimental evaluation using several state-of-the-art lightweight LLMs. We test them with several publicly available datasets specifically designed for edge and IoT scenarios and different edge nodes with varying computational power and characteristics.

The ability to extract value from historical data is essential for enterprise decision-making. However, much of this information remains inaccessible within large legacy file systems that lack structured organization and semantic indexing, making retrieval and analysis inefficient and error-prone. We introduce SPAR (Session-based Pipeline for Adaptive Retrieval), a conceptual framework that integrates Large Language Models (LLMs) into a Retrieval-Augmented Generation (RAG) architecture specifically designed for legacy enterprise environments. Unlike conventional RAG pipelines, which require costly construction and maintenance of full-scale vector databases that mirror the entire file system, SPAR employs a lightweight two-stage process: a semantic Metadata Index is first created, after which session-specific vector databases are dynamically generated on demand. This design reduces computational overhead while improving transparency, controllability, and relevance in retrieval. We provide a theoretical complexity analysis comparing SPAR with standard LLM-based RAG pipelines, demonstrating its computational advantages. To validate the framework, we apply SPAR to a synthesized enterprise-scale file system containing a large corpus of biomedical literature, showing improvements in both retrieval effectiveness and downstream model accuracy. Finally, we discuss design trade-offs and outline open challenges for deploying SPAR across diverse enterprise settings.

Path planning in dynamic environments remains a core challenge in robotics, especially as autonomous systems are deployed in unpredictable spaces such as warehouses and public roads. While algorithms like Fast Marching Tree (FMT^{*}) offer asymptotically optimal solutions in static settings, their single-pass design prevents path revisions which are essential for real-time adaptation. On the other hand, full replanning is often too computationally expensive. This paper introduces FMT^{x}, an extension of the Fast Marching Tree algorithm that enables efficient and consistent replanning in dynamic environments. We revisit the neighbor selection rule of FMT^{*} and demonstrate that a minimal change overcomes its single-pass limitation, enabling the algorithm to update cost-to-come values upon discovering better connections without sacrificing asymptotic optimality or computational efficiency. By maintaining a cost-ordered priority queue and applying a selective update condition that uses an expanding neighbor to identify and trigger the re-evaluation of any node with a potentially suboptimal path, FMT^{x} ensures that suboptimal routes are efficiently repaired as the environment evolves. This targeted strategy preserves the inherent efficiency of FMT^{*} while enabling robust adaptation to changes in obstacle configuration. FMT^{x} is proven to recover an asymptotically optimal solution after environmental changes. Experimental results demonstrate that FMT^{x} outperforms the influential replanner RRT^{x}, reacting more swiftly to dynamic events with lower computational overhead and thus offering a more effective solution for real-time robotic navigation in unpredictable worlds.

Recent advancements in Visual Language Models (VLMs) have made them crucial for visual question answering (VQA) in autonomous driving, enabling natural human-vehicle interactions. However, existing methods often struggle in dynamic driving environments, as they usually focus on static images or videos and rely on downsampling to manage computational costs. This results in the loss of critical details and the difficulty in effectively integrating spatial and temporal information, undermining fine-grained perception and temporal coherence essential for effective decision-making. To tackle these challenges, we introduce LaVida Drive, a novel and efficient VQA framework for autonomous driving. LaVida Drive seamlessly integrates temporal data while maintaining high-resolution inputs for detailed visual perception. It optimizes spatial processing by retaining high-resolution data for intricate details and using lower-resolution inputs for temporal analysis to focus on motion-related features, thereby boosting computational efficiency. The core of LaVida Drive consists of two modules: the Query-aware Token Selection module and the Spatial-Temporal Token Recovery and Enhancement module. The former dynamically selects the most relevant visual tokens based on semantic alignment with the input query, reducing the token count from high-resolution spatial input. The latter ensures smooth and coherent interactions between spatial and temporal information, preserving contextual continuity across frames. Extensive experiments on various autonomous driving question-answering benchmarks show that LaVida Drive significantly reduces visual tokens, enhances efficiency, and improves overall performance.

Large Language Models (LLMs) have showcased exceptional capabilities in various domains, attracting significant interest from both academia and industry. Despite their impressive performance, the substantial size and computational demands of LLMs pose considerable challenges for practical deployment, particularly in environments with limited resources. The endeavor to compress language models while maintaining their accuracy has become a focal point of research. Among the various methods, knowledge distillation has emerged as an effective technique to enhance inference speed without greatly compromising performance. This paper presents a thorough survey from three aspects: method, evaluation, and application, exploring knowledge distillation techniques tailored specifically for LLMs. Specifically, we divide the methods into white-box KD and black-box KD to better illustrate their differences. Furthermore, we also explored the evaluation tasks and distillation effects between different distillation methods, and proposed directions for future research. Through in-depth understanding of the latest advancements and practical applications, this survey provides valuable resources for researchers, paving the way for sustained progress in this field.

Large-scale multi-modal deep learning models have revolutionized domains such as healthcare, highlighting the importance of computational power. However, in resource-constrained regions like Low and Middle-Income Countries (LMICs), limited access to GPUs and data poses significant challenges, often leaving CPUs as the sole resource. To address this, we advocate for leveraging vector embeddings to enable flexible and efficient computational methodologies, democratizing multimodal deep learning across diverse contexts. Our paper investigates the efficiency and effectiveness of using vector embeddings from single-modal foundation models and multi-modal Vision-Language Models (VLMs) for multimodal deep learning in low-resource environments, particularly in healthcare. Additionally, we propose a simple yet effective inference-time method to enhance performance by aligning image-text embeddings. Comparing these approaches with traditional methods, we assess their impact on computational efficiency and model performance using metrics like accuracy, F1-score, inference time, training time, and memory usage across three medical modalities: BRSET (ophthalmology), HAM10000 (dermatology), and SatelliteBench (public health). Our findings show that embeddings reduce computational demands without compromising model performance. Furthermore, our alignment method improves performance in medical tasks. This research promotes sustainable AI practices by optimizing resources in constrained environments, highlighting the potential of embedding-based approaches for efficient multimodal learning. Vector embeddings democratize multimodal deep learning in LMICs, particularly in healthcare, enhancing AI adaptability in varied use cases.

With the continuous growth in the number of parameters of transformer-based pretrained language models (PLMs), particularly the emergence of large language models (LLMs) with billions of parameters, many natural language processing (NLP) tasks have demonstrated remarkable success. However, the enormous size and computational demands of these models pose significant challenges for adapting them to specific downstream tasks, especially in environments with limited computational resources. Parameter Efficient Fine-Tuning (PEFT) offers an effective solution by reducing the number of fine-tuning parameters and memory usage while achieving comparable performance to full fine-tuning. The demands for fine-tuning PLMs, especially LLMs, have led to a surge in the development of PEFT methods, as depicted in Fig. 1. In this paper, we present a comprehensive and systematic review of PEFT methods for PLMs. We summarize these PEFT methods, discuss their applications, and outline future directions. Furthermore, we conduct experiments using several representative PEFT methods to better understand their effectiveness in parameter efficiency and memory efficiency. By offering insights into the latest advancements and practical applications, this survey serves as an invaluable resource for researchers and practitioners seeking to navigate the challenges and opportunities presented by PEFT in the context of PLMs.

Large Language Models (LLMs) have revolutionized natural language processing tasks with remarkable success. However, their formidable size and computational demands present significant challenges for practical deployment, especially in resource-constrained environments. As these challenges become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate these limitations. This paper presents a comprehensive survey that navigates the landscape of model compression techniques tailored specifically for LLMs. Addressing the imperative need for efficient deployment, we delve into various methodologies, encompassing quantization, pruning, knowledge distillation, and more. Within each of these techniques, we highlight recent advancements and innovative approaches that contribute to the evolving landscape of LLM research. Furthermore, we explore benchmarking strategies and evaluation metrics that are essential for assessing the effectiveness of compressed LLMs. By providing insights into the latest developments and practical implications, this survey serves as an invaluable resource for both researchers and practitioners. As LLMs continue to evolve, this survey aims to facilitate enhanced efficiency and real-world applicability, establishing a foundation for future advancements in the field.

The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct deployment in resource-constrained edge environments. This creates a critical need for high-performance small models that can operate efficiently at the edge. Yet, after pre-training alone, these smaller models often fail to meet the performance requirements of complex tasks. To bridge this gap, we introduce a systematic post-training pipeline that efficiently enhances small model accuracy. Our post training pipeline consists of curriculum-based supervised fine-tuning (SFT) and offline on-policy knowledge distillation. The resulting instruction-tuned model achieves state-of-the-art performance among billion-parameter models, demonstrating strong generalization under strict hardware constraints while maintaining competitive accuracy across a variety of tasks. This work provides a practical and efficient solution for developing high-performance language models on Ascend edge devices.

Recent advancements in large language models (LLMs) have expanded their capabilities beyond traditional text-based tasks to multimodal domains, integrating visual, auditory, and textual data. While multimodal LLMs have been extensively explored for high-level planning in domains like robotics and games, their potential as low-level controllers remains largely untapped. This paper explores the application of multimodal LLMs as low-level controllers in the domain of Atari video games, introducing Atari game performance as a new benchmark for evaluating the ability of multimodal LLMs to perform low-level control tasks. Unlike traditional reinforcement learning (RL) and imitation learning (IL) methods that require extensive computational resources as well as reward function specification, these LLMs utilize pre-existing multimodal knowledge to directly engage with game environments. Our study assesses multiple multimodal LLMs performance against traditional RL agents, human players, and random agents, focusing on their ability to understand and interact with complex visual scenes and formulate strategic responses. Additionally, we examine the impact of In-Context Learning (ICL) by incorporating human-demonstrated game-play trajectories to enhance the models contextual understanding. Through this investigation, we aim to determine the extent to which multimodal LLMs can leverage their extensive training to effectively function as low-level controllers, thereby redefining potential applications in dynamic and visually complex environments. Additional results and videos are available at our project webpage: https://sites.google.com/view/atari-gpt/.

Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform effortlessly. This discrepancy highlights a critical gap between declarative knowledge (knowing about something) and procedural knowledge (knowing how to do something). Although traditional reinforcement learning (RL) agents can acquire procedural knowledge through environmental interaction, they often operate as black boxes and require substantial training data. In contrast, LLMs possess extensive world knowledge and reasoning capabilities, but are unable to effectively convert this static knowledge into dynamic decision-making in interactive settings. To address this challenge, we propose Think in Games (TiG), a novel framework that empowers LLMs to develop procedural understanding through direct interaction with game environments, while retaining their inherent reasoning and explanatory abilities. Specifically, TiG reformulates RL-based decision-making as a language modeling task: LLMs generate language-guided policies, which are refined iteratively through online reinforcement learning based on environmental feedback. Our experimental results show that TiG successfully bridges the gap between declarative and procedural knowledge, achieving competitive performance with dramatically lower data and computational demands compared to conventional RL methods. Moreover, TiG provides step-by-step natural language explanations for its decisions, greatly improving transparency and interpretability in complex interactive tasks.

We propose a novel memory mechanism to build video generators that can explore environments interactively. Similar results have previously been achieved by out-painting 2D views of the scene while incrementally reconstructing its 3D geometry, which quickly accumulates errors, or by video generators with a short context window, which struggle to maintain scene coherence over the long term. To address these limitations, we introduce Surfel-Indexed View Memory (VMem), a mechanism that remembers past views by indexing them geometrically based on the 3D surface elements (surfels) they have observed. VMem enables the efficient retrieval of the most relevant past views when generating new ones. By focusing only on these relevant views, our method produces consistent explorations of imagined environments at a fraction of the computational cost of using all past views as context. We evaluate our approach on challenging long-term scene synthesis benchmarks and demonstrate superior performance compared to existing methods in maintaining scene coherence and camera control.

Existing Visual-Language-Action (VLA) models have shown promising performance in zero-shot scenarios, demonstrating impressive task execution and reasoning capabilities. However, a significant challenge arises from the limitations of visual encoding, which can result in failures during tasks such as object grasping. Moreover, these models typically suffer from high computational overhead due to their large sizes, often exceeding 7B parameters. While these models excel in reasoning and task planning, the substantial computational overhead they incur makes them impractical for real-time robotic environments, where speed and efficiency are paramount. To address the limitations of existing VLA models, we propose NORA, a 3B-parameter model designed to reduce computational overhead while maintaining strong task performance. NORA adopts the Qwen-2.5-VL-3B multimodal model as its backbone, leveraging its superior visual-semantic understanding to enhance visual reasoning and action grounding. Additionally, our is trained on 970k real-world robot demonstrations and equipped with the FAST+ tokenizer for efficient action sequence generation. Experimental results demonstrate that NORA outperforms existing large-scale VLA models, achieving better task performance with significantly reduced computational overhead, making it a more practical solution for real-time robotic autonomy.

This study evaluates the performance of classical and modern control methods for real-world Cable-Driven Parallel Robots (CDPRs), focusing on underconstrained systems with limited time discretization. A comparative analysis is conducted between classical PID controllers and modern reinforcement learning algorithms, including Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO), and Trust Region Policy Optimization (TRPO). The results demonstrate that TRPO outperforms other methods, achieving the lowest root mean square (RMS) errors across various trajectories and exhibiting robustness to larger time intervals between control updates. TRPO's ability to balance exploration and exploitation enables stable control in noisy, real-world environments, reducing reliance on high-frequency sensor feedback and computational demands. These findings highlight TRPO's potential as a robust solution for complex robotic control tasks, with implications for dynamic environments and future applications in sensor fusion or hybrid control strategies.

The recent advancements of Small Language Models (SLMs) have opened new possibilities for efficient code generation. SLMs offer lightweight and cost-effective alternatives to Large Language Models (LLMs), making them attractive for use in resource-constrained environments. However, empirical understanding of SLMs, particularly their capabilities, limitations, and performance trade-offs in code generation remains limited. This study presents a comprehensive empirical evaluation of 20 open-source SLMs ranging from 0.4B to 10B parameters on five diverse code-related benchmarks (HumanEval, MBPP, Mercury, HumanEvalPack, and CodeXGLUE). The models are assessed along three dimensions: i) functional correctness of generated code, ii) computational efficiency and iii) performance across multiple programming languages. The findings of this study reveal that several compact SLMs achieve competitive results while maintaining a balance between performance and efficiency, making them viable for deployment in resource-constrained environments. However, achieving further improvements in accuracy requires switching to larger models. These models generally outperform their smaller counterparts, but they require much more computational power. We observe that for 10% performance improvements, models can require nearly a 4x increase in VRAM consumption, highlighting a trade-off between effectiveness and scalability. Besides, the multilingual performance analysis reveals that SLMs tend to perform better in languages such as Python, Java, and PHP, while exhibiting relatively weaker performance in Go, C++, and Ruby. However, statistical analysis suggests these differences are not significant, indicating a generalizability of SLMs across programming languages. Based on the findings, this work provides insights into the design and selection of SLMs for real-world code generation tasks.

Navigation and mapping on the lunar surface require robust perception under challenging conditions, including poorly textured environments, high-contrast lighting, and limited computational resources. This paper presents a real-time mapping framework that integrates dense perception models with a 3D Gaussian Splatting (3DGS) representation. We first benchmark several models on synthetic datasets generated with the LuPNT simulator, selecting a stereo dense depth estimation model based on Gated Recurrent Units for its balance of speed and accuracy in depth estimation, and a convolutional neural network for its superior performance in detecting semantic segments. Using ground truth poses to decouple the local scene understanding from the global state estimation, our pipeline reconstructs a 120-meter traverse with a geometric height accuracy of approximately 3 cm, outperforming a traditional point cloud baseline without LiDAR. The resulting 3DGS map enables novel view synthesis and serves as a foundation for a full SLAM system, where its capacity for joint map and pose optimization would offer significant advantages. Our results demonstrate that combining semantic segmentation and dense depth estimation with learned map representations is an effective approach for creating detailed, large-scale maps to support future lunar surface missions.

The integration of agentic AI, powered by large language models (LLMs) with autonomous reasoning, planning, and execution, into unmanned aerial vehicle (UAV) swarms opens new operational possibilities and brings the vision of the Internet of Drones closer to reality. However, infrastructure constraints, dynamic environments, and the computational demands of multi-agent coordination limit real-world deployment in high-risk scenarios such as wildfires and disaster response. This paper investigates the integration of LLM-based agentic AI and edge computing to realize scalable and resilient autonomy in UAV swarms. We first discuss three architectures for supporting UAV swarms - standalone, edge-enabled, and edge-cloud hybrid deployment - each optimized for varying autonomy and connectivity levels. Then, a use case for wildfire search and rescue (SAR) is designed to demonstrate the efficiency of the edge-enabled architecture, enabling high SAR coverage, reduced mission completion times, and a higher level of autonomy compared to traditional approaches. Finally, we highlight open challenges in integrating LLMs and edge computing for mission-critical UAV-swarm applications.

Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content while exploring new scenes and preserve spatial consistency when revisiting explored areas. Under limited computation budgets, it must compress and exploit historical cues within a finite context window, which exposes a trade-off: Temporal-only memory lacks long-term spatial consistency, whereas adding spatial memory strengthens consistency but may degrade new scene generation quality when the model over-relies on insufficient spatial context. We present Memory Forcing, a learning framework that pairs training protocols with a geometry-indexed spatial memory. Hybrid Training exposes distinct gameplay regimes, guiding the model to rely on temporal memory during exploration and incorporate spatial memory for revisits. Chained Forward Training extends autoregressive training with model rollouts, where chained predictions create larger pose variations and encourage reliance on spatial memory for maintaining consistency. Point-to-Frame Retrieval efficiently retrieves history by mapping currently visible points to their source frames, while Incremental 3D Reconstruction maintains and updates an explicit 3D cache. Extensive experiments demonstrate that Memory Forcing achieves superior long-term spatial consistency and generative quality across diverse environments, while maintaining computational efficiency for extended sequences.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

Fluorescence LiDAR (FLiDAR), a Light Detection and Ranging (LiDAR) technology employed for distance and depth estimation across medical, automotive, and other fields, encounters significant computational challenges in scattering media. The complex nature of the acquired FLiDAR signal, particularly in such environments, makes isolating photon time-of-flight (related to target depth) and intrinsic fluorescence lifetime exceptionally difficult, thus limiting the effectiveness of current analytical and computational methodologies. To overcome this limitation, we present a Physics-Guided Mixture-of-Experts (MoE) framework tailored for specialized modeling of diverse temporal components. In contrast to the conventional MoE approaches our expert models are informed by underlying physics, such as the radiative transport equation governing photon propagation in scattering media. Central to our approach is EvidenceMoE, which integrates Evidence-Based Dirichlet Critics (EDCs). These critic models assess the reliability of each expert's output by providing per-expert quality scores and corrective feedback. A Decider Network then leverages this information to fuse expert predictions into a robust final estimate adaptively. We validate our method using realistically simulated Fluorescence LiDAR (FLiDAR) data for non-invasive cancer cell depth detection generated from photon transport models in tissue. Our framework demonstrates strong performance, achieving a normalized root mean squared error (NRMSE) of 0.030 for depth estimation and 0.074 for fluorescence lifetime.

Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model architectures and have varying computational resources. Such heterogeneity complicates the aggregation process, leading to performance bottlenecks and reduced model generalizability. To address these issues, we propose FedADP, a federated learning framework designed to adapt to client heterogeneity by dynamically adjusting model architectures during aggregation. FedADP enables effective collaboration among clients with differing capabilities, maximizing resource utilization and ensuring model quality. Our experimental results demonstrate that FedADP significantly outperforms existing methods, such as FlexiFed, achieving an accuracy improvement of up to 23.30%, thereby enhancing model adaptability and training efficiency in heterogeneous real-world settings.

In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at capturing global context through self-attention mechanisms, their deployment in resource-limited environments is hindered by computational complexity and latency. Conversely, lightweight CNNs are favored for their parameter efficiency and low latency. This study investigates the complementary advantages of CNNs and ViTs to develop a versatile vision backbone tailored for resource-constrained applications. We introduce RepNeXt, a novel model series integrates multi-scale feature representations and incorporates both serial and parallel structural reparameterization (SRP) to enhance network depth and width without compromising inference speed. Extensive experiments demonstrate RepNeXt's superiority over current leading lightweight CNNs and ViTs, providing advantageous latency across various vision benchmarks. RepNeXt-M4 matches RepViT-M1.5's 82.3\% accuracy on ImageNet within 1.5ms on an iPhone 12, outperforms its AP^{box} by 1.3 on MS-COCO, and reduces parameters by 0.7M. Codes and models are available at https://github.com/suous/RepNeXt.

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models are progressively endowed with strong general capabilities, standard Vision Transformer (ViT) encoders remain a critical bottleneck, suffering from excessive latency and memory consumption when processing high-resolution inputs.To address these challenges, we introduce HyperVL, an efficient multimodal large language model tailored for on-device inference. HyperVL adopts an image-tiling strategy to cap peak memory usage and incorporates two novel techniques: (1) a Visual Resolution Compressor (VRC) that adaptively predicts optimal encoding resolutions to eliminate redundant computation, and (2) Dual Consistency Learning (DCL), which aligns multi-scale ViT encoders within a unified framework, enabling dynamic switching between visual branches under a shared LLM. Extensive experiments demonstrate that HyperVL achieves state-of-the-art performance among models of comparable size across multiple benchmarks. Furthermore, it significantly significantly reduces latency and power consumption on real mobile devices, demonstrating its practicality for on-device multimodal inference.

Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures. These requirements severely limit accessibility for researchers and practitioners who lack substantial computational resources. In this paper, we introduce \model, an efficient training paradigm for image generation models that uses knowledge distillation (KD) and Direct Preference Optimization (DPO). Drawing inspiration from the success of data KD techniques widely adopted in Multi-Modal Large Language Models (MLLMs), LightGen distills knowledge from state-of-the-art (SOTA) text-to-image models into a compact Masked Autoregressive (MAR) architecture with only 0.7B parameters. Using a compact synthetic dataset of just 2M high-quality images generated from varied captions, we demonstrate that data diversity significantly outweighs data volume in determining model performance. This strategy dramatically reduces computational demands and reduces pre-training time from potentially thousands of GPU-days to merely 88 GPU-days. Furthermore, to address the inherent shortcomings of synthetic data, particularly poor high-frequency details and spatial inaccuracies, we integrate the DPO technique that refines image fidelity and positional accuracy. Comprehensive experiments confirm that LightGen achieves image generation quality comparable to SOTA models while significantly reducing computational resources and expanding accessibility for resource-constrained environments. Code is available at https://github.com/XianfengWu01/LightGen

The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages. To address this, we introduce MEnvAgent, a Multi-language framework for automated Environment construction that facilitates scalable generation of verifiable task instances. MEnvAgent employs a multi-agent Planning-Execution-Verification architecture to autonomously resolve construction failures and integrates a novel Environment Reuse Mechanism that reduces computational overhead by incrementally patching historical environments. Evaluations on MEnvBench, a new benchmark comprising 1,000 tasks across 10 languages, demonstrate that MEnvAgent outperforms baselines, improving Fail-to-Pass (F2P) rates by 8.6% while reducing time costs by 43%. Additionally, we demonstrate the utility of MEnvAgent by constructing MEnvData-SWE, the largest open-source polyglot dataset of realistic verifiable Docker environments to date, alongside solution trajectories that enable consistent performance gains on SWE tasks across a wide range of models. Our code, benchmark, and dataset are available at https://github.com/ernie-research/MEnvAgent.

Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling techniques, but existing methods are typically computationally demanding, contradicting the resource-efficient design goals of small models. To address these limitations, we propose two novel and efficient test-time scaling strategies that leverage the model-internal features rather than external supervision: (i) Test-Time Augmentation (TTAug), which generates multiple augmented inputs and aggregates outputs at the token level without parameter updates, and (ii) Test-Time Adaptation (TTAdapt), which adapts model parameters during inference using consensus-based pseudolabels from TTAug. Through extensive experiments across nine benchmarks, we demonstrate consistent performance improvements while maintaining computational efficiency suitable for resource-constrained environments. The generality of our approach is demonstrated both within models at different scales and across different VLMs without additional tuning.

The ongoing evolution of language models has led to the development of large-scale architectures that demonstrate exceptional performance across a wide range of tasks. However, these models come with significant computational and energy demands, as well as potential privacy implications. In this context, Small Reasoning Language Models (SRLMs) with approximately 0.5 billion parameters present a compelling alternative due to their remarkable computational efficiency and cost effectiveness, particularly in resource-constrained environments. Despite these advantages, the limited capacity of 0.5 billion parameter models poses challenges in handling complex tasks such as mathematical reasoning and code generation. This research investigates various training strategies, including supervised fine-tuning (SFT), knowledge distillation (KD), and reinforcement learning (RL), as well as their hybrid implementations, to enhance the performance of 0.5B SRLMs. We analyze effective methodologies to bridge the performance gap between SRLMS and larger models and present insights into optimal training pipelines tailored for these smaller architectures. Through extensive experimental validation and analysis, our work aims to provide actionable recommendations for maximizing the reasoning capabilities of 0.5B models.

Cooperative perception through Vehicle-to-Everything (V2X) communication offers significant potential for enhancing vehicle perception by mitigating occlusions and expanding the field of view. However, past research has predominantly focused on improving accuracy metrics without addressing the crucial system-level considerations of efficiency, latency, and real-world deployability. Noticeably, most existing systems rely on full-precision models, which incur high computational and transmission costs, making them impractical for real-time operation in resource-constrained environments. In this paper, we introduce QuantV2X, the first fully quantized multi-agent system designed specifically for efficient and scalable deployment of multi-modal, multi-agent V2X cooperative perception. QuantV2X introduces a unified end-to-end quantization strategy across both neural network models and transmitted message representations that simultaneously reduces computational load and transmission bandwidth. Remarkably, despite operating under low-bit constraints, QuantV2X achieves accuracy comparable to full-precision systems. More importantly, when evaluated under deployment-oriented metrics, QuantV2X reduces system-level latency by 3.2times and achieves a +9.5 improvement in mAP30 over full-precision baselines. Furthermore, QuantV2X scales more effectively, enabling larger and more capable models to fit within strict memory budgets. These results highlight the viability of a fully quantized multi-agent intermediate fusion system for real-world deployment. The system will be publicly released to promote research in this field: https://github.com/ucla-mobility/QuantV2X.

Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various chart understanding tasks. However, the sheer size of these models in terms of parameters and computational requirements limits their use in resource-constrained environments. In this paper, we present TinyChart, an efficient MLLM for chart understanding with only 3B parameters. TinyChart overcomes two key challenges in efficient chart understanding: (1) reduce the burden of learning numerical computations through a Program-of-Thoughts (PoT) learning strategy, which trains the model to generate Python programs for numerical calculations, and (2) reduce lengthy vision feature sequences produced by the vision transformer for high-resolution images through a Vision Token Merging module, which gradually merges most similar vision tokens. Extensive experiments demonstrate that our 3B TinyChart achieves SOTA performance on a variety of chart understanding benchmarks including ChartQA, Chart-to-Text, Chart-to-Table, OpenCQA, and ChartX. It outperforms several chart understanding MLLM with up to 13B parameters such as ChartLlama and ChartAst, and close-sourced general-purpose MLLM GPT-4V on ChartQA. It also demonstrates its superior efficiency with higher throughput during inference due to a smaller model scale and more efficient vision encoding. Our code and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/TinyChart.

The increasing interest in Large Language Models (LLMs) within the telecommunications sector underscores their potential to revolutionize operational efficiency. However, the deployment of these sophisticated models is often hampered by their substantial size and computational demands, raising concerns about their viability in resource-constrained environments. Addressing this challenge, recent advancements have seen the emergence of small language models that surprisingly exhibit performance comparable to their larger counterparts in many tasks, such as coding and common-sense reasoning. Phi-2, a compact yet powerful model, exemplifies this new wave of efficient small language models. This paper conducts a comprehensive evaluation of Phi-2's intrinsic understanding of the telecommunications domain. Recognizing the scale-related limitations, we enhance Phi-2's capabilities through a Retrieval-Augmented Generation approach, meticulously integrating an extensive knowledge base specifically curated with telecom standard specifications. The enhanced Phi-2 model demonstrates a profound improvement in accuracy, answering questions about telecom standards with a precision that closely rivals the more resource-intensive GPT-3.5. The paper further explores the refined capabilities of Phi-2 in addressing problem-solving scenarios within the telecom sector, highlighting its potential and limitations.

Customer-service question answering (QA) systems increasingly rely on conversational language understanding. While Large Language Models (LLMs) achieve strong performance, their high computational cost and deployment constraints limit practical use in resource-constrained environments. Small Language Models (SLMs) provide a more efficient alternative, yet their effectiveness for multi-turn customer-service QA remains underexplored, particularly in scenarios requiring dialogue continuity and contextual understanding. This study investigates instruction-tuned SLMs for context-summarized multi-turn customer-service QA, using a history summarization strategy to preserve essential conversational state. We also introduce a conversation stage-based qualitative analysis to evaluate model behavior across different phases of customer-service interactions. Nine instruction-tuned low-parameterized SLMs are evaluated against three commercial LLMs using lexical and semantic similarity metrics alongside qualitative assessments, including human evaluation and LLM-as-a-judge methods. Results show notable variation across SLMs, with some models demonstrating near-LLM performance, while others struggle to maintain dialogue continuity and contextual alignment. These findings highlight both the potential and current limitations of low-parameterized language models for real-world customer-service QA systems.

Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving often struggle with resource inefficiencies, leading to high operational costs, latency issues, and limited scalability. This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally improve LLM inference serving. By leveraging these technologies, we demonstrate how a Cloud Native system enables more efficient resource allocation, reduces latency, and enhances throughput in high-demand scenarios. Through real-world evaluations using Kubernetes-based autoscaling, we show that Cloud Native architectures can dynamically adapt to workload fluctuations, mitigating performance bottlenecks while optimizing LLM inference serving performance. This discussion provides a broader perspective on how Cloud Native frameworks could reshape the future of scalable LLM inference serving, offering key insights for researchers, practitioners, and industry leaders in cloud computing and artificial intelligence.

Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank decomposition methods offer a promising path for structural compression, they often suffer from accuracy degradation, expensive calibration procedures, and result in inefficient model architectures that hinder real-world inference speedups. In this paper, we propose FLAT-LLM, a fast and accurate, training-free structural compression method based on fine-grained low-rank transformations in the activation space. Specifically, we reduce the hidden dimension by transforming the weights using truncated eigenvectors computed via head-wise Principal Component Analysis, and employ a greedy budget redistribution strategy to adaptively allocate ranks across decoders. FLAT-LLM achieves efficient and effective weight compression without recovery fine-tuning, which could complete the calibration within a few minutes. Evaluated across 5 models and 11 datasets, FLAT-LLM outperforms structural pruning baselines in generalization and downstream performance, while delivering inference speedups over decomposition-based methods.

Large language models (LLMs) exhibit remarkable performance across various natural language processing tasks but suffer from immense computational and memory demands, limiting their deployment in resource-constrained environments. To address this challenge, we propose NoWag: (Normalized Weight and Activation Guided Compression), a unified framework for zero-shot shape preserving compression algorithms. We compressed Llama-2 7B/13B/70B and Llama-3 8/70BB models, using two popular forms of shape-preserving compression, vector quantization NoWag-VQ (NoWag for Vector Quantization), and unstructured/semi-structured pruning NoWag-P (NoWag for Pruning). We found that NoWag-VQ significantly outperforms state-of-the-art zero shot VQ, and that NoWag-P performs competitively against state-of-the-art methods. These results suggest commonalities between these compression paradigms that could inspire future work. Our code is available at https://github.com/LawrenceRLiu/NoWag

Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (clients) collaboratively to train on decentralized data. In practice, FL often faces statistical, system, and model heterogeneities, which inspires the field of Model-Heterogeneous Personalized Federated Learning (MHPFL). With the increased interest in adopting large language models (LLMs) in FL, the existing MHPFL methods cannot achieve acceptable computational and communication costs, while maintaining satisfactory model performance. To bridge this gap, we propose a novel and efficient model-heterogeneous personalized Federated learning framework based on LoRA tuning (pFedLoRA). Inspired by the popular LoRA method for fine-tuning pre-trained LLMs with a low-rank model (a.k.a., an adapter), we design a homogeneous small adapter to facilitate federated client's heterogeneous local model training with our proposed iterative training for global-local knowledge exchange. The homogeneous small local adapters are aggregated on the FL server to generate a global adapter. We theoretically prove the convergence of pFedLoRA. Extensive experiments on two benchmark datasets demonstrate that pFedLoRA outperforms six state-of-the-art baselines, beating the best method by 1.35% in test accuracy, 11.81 times computation overhead reduction and 7.41 times communication cost saving.

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders, leading to high computational demands, which limits their applicability in resource-constrained environments and for long-context tasks. In this work, we propose a training-free adaptive inference method for multi-modal LLMs that can accommodate a broad range of efficiency requirements with a minimum performance drop. Our method consists of a) iterative token merging based on embedding similarity before LLMs, and b) progressive token pruning within LLM layers based on multi-modal importance. With a minimalist design, our method can be applied to both video and image LLMs. Extensive experiments on diverse video and image benchmarks demonstrate that, our method substantially reduces computation load (e.g., a 7-fold reduction in FLOPs) while preserving the performance of video and image LLMs. Further, under a similar computational cost, our method outperforms the state-of-the-art methods in long video understanding (e.g., +4.6 on MLVU). Additionally, our in-depth analysis provides insights into token redundancy and LLM layer behaviors, offering guidance for future research in designing efficient multi-modal LLMs. Our code will be available at https://github.com/LaVi-Lab/AIM.

The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in the high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus: computational, memory, energy, financial, and network resources and their applicability across various stages of an LLM's lifecycle, including architecture design, pretraining, finetuning, and system design. Additionally, the survey introduces a nuanced categorization of resource efficiency techniques by their specific resource types, which uncovers the intricate relationships and mappings between various resources and corresponding optimization techniques. A standardized set of evaluation metrics and datasets is also presented to facilitate consistent and fair comparisons across different models and techniques. By offering a comprehensive overview of the current sota and identifying open research avenues, this survey serves as a foundational reference for researchers and practitioners, aiding them in developing more sustainable and efficient LLMs in a rapidly evolving landscape.

In online reinforcement learning (online RL), balancing exploration and exploitation is crucial for finding an optimal policy in a sample-efficient way. To achieve this, existing sample-efficient online RL algorithms typically consist of three components: estimation, planning, and exploration. However, in order to cope with general function approximators, most of them involve impractical algorithmic components to incentivize exploration, such as optimization within data-dependent level-sets or complicated sampling procedures. To address this challenge, we propose an easy-to-implement RL framework called Maximize to Explore (MEX), which only needs to optimize unconstrainedly a single objective that integrates the estimation and planning components while balancing exploration and exploitation automatically. Theoretically, we prove that MEX achieves a sublinear regret with general function approximations for Markov decision processes (MDP) and is further extendable to two-player zero-sum Markov games (MG). Meanwhile, we adapt deep RL baselines to design practical versions of MEX, in both model-free and model-based manners, which can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards. Compared with existing sample-efficient online RL algorithms with general function approximations, MEX achieves similar sample efficiency while enjoying a lower computational cost and is more compatible with modern deep RL methods.

Passive acoustic monitoring has become a key strategy in biodiversity assessment, conservation, and behavioral ecology, especially as Internet-of-Things (IoT) devices enable continuous in situ audio collection at scale. While recent self-supervised learning (SSL)-based audio encoders, such as BEATs and AVES, have shown strong performance in bioacoustic tasks, their computational cost and limited robustness to unseen environments hinder deployment on resource-constrained platforms. In this work, we introduce BioME, a resource-efficient audio encoder designed for bioacoustic applications. BioME is trained via layer-to-layer distillation from a high-capacity teacher model, enabling strong representational transfer while reducing the parameter count by 75%. To further improve ecological generalization, the model is pretrained on multi-domain data spanning speech, environmental sounds, and animal vocalizations. A key contribution is the integration of modulation-aware acoustic features via FiLM conditioning, injecting a DSP-inspired inductive bias that enhances feature disentanglement in low-capacity regimes. Across multiple bioacoustic tasks, BioME matches or surpasses the performance of larger models, including its teacher, while being suitable for resource-constrained IoT deployments. For reproducibility, code and pretrained checkpoints are publicly available.

Reliable odometry is essential for mobile robots as they increasingly enter more challenging environments, which often contain little information to constrain point cloud registration, resulting in degraded LiDAR-Inertial Odometry (LIO) accuracy or even divergence. To address this, we present BIEVR-LIO, a novel approach designed specifically to exploit subtle variations in the available geometry for improved robustness. We propose a high-resolution map representation that stores surfaces as compact voxel-wise oriented height images. This representation can directly be used for registration without the calculation of intermediate geometric primitives while still supporting efficient updates. Since informative geometry is often sparsely distributed in the environment, we further propose a map-informed point sampling strategy to focus registration on geometrically informative regions, improving robustness in uninformative environments while reducing computational cost compared to global high-resolution sampling. Experiments across multiple sensors, platforms, and environments demonstrates state-of-the-art performance in well-constrained scenes and substantial improvements in challenging scenarios where baseline methods diverge. Additionally, we demonstrate that the fine-grained geometry captured by BIEVR-LIO can be used for downstream tasks such as elevation mapping for robot locomotion.

End-to-end autonomous driving policies based on Imitation Learning (IL) often struggle in closed-loop execution due to the misalignment between inadequate open-loop training objectives and real driving requirements. While Reinforcement Learning (RL) offers a solution by directly optimizing driving goals via reward signals, the rendering-based training environments introduce the rendering gap and are inefficient due to high computational costs. To overcome these challenges, we present a novel Pseudo-simulation-based RL method for closed-loop end-to-end autonomous driving, PerlAD. Based on offline datasets, PerlAD constructs a pseudo-simulation that operates in vector space, enabling efficient, rendering-free trial-and-error training. To bridge the gap between static datasets and dynamic closed-loop environments, PerlAD introduces a prediction world model that generates reactive agent trajectories conditioned on the ego vehicle's plan. Furthermore, to facilitate efficient planning, PerlAD utilizes a hierarchical decoupled planner that combines IL for lateral path generation and RL for longitudinal speed optimization. Comprehensive experimental results demonstrate that PerlAD achieves state-of-the-art performance on the Bench2Drive benchmark, surpassing the previous E2E RL method by 10.29% in Driving Score without requiring expensive online interactions. Additional evaluations on the DOS benchmark further confirm its reliability in handling safety-critical occlusion scenarios.

Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large cloud-based models, which are difficult to deploy in clinical environments due to privacy constraints and computational requirements. In this work, we investigate how far grounded EHR question answering can be pushed when restricted to a single notebook. We participate in all four subtasks of the ArchEHR-QA 2026 shared task and evaluate several approaches designed to run on commodity hardware. All experiments are conducted locally without external APIs or cloud infrastructure. Our results show that such systems can achieve competitive performance on the shared task leaderboards. In particular, our submissions perform above average in two subtasks, and we observe that smaller models can approach the performance of much larger systems when properly configured. These findings suggest that privacy-preserving EHR QA systems running fully locally are feasible with current models and commodity hardware. The source code is available at https://github.com/ibrahimey/ArchEHR-QA-2026.

In recent work on time-series prediction, Transformers and even large language models have garnered significant attention due to their strong capabilities in sequence modeling. However, in practical deployments, time-series prediction often requires operation in resource-constrained environments, such as edge devices, which are unable to handle the computational overhead of large models. To address such scenarios, some lightweight models have been proposed, but they exhibit poor performance on non-stationary sequences. In this paper, we propose SWIFT, a lightweight model that is not only powerful, but also efficient in deployment and inference for Long-term Time Series Forecasting (LTSF). Our model is based on three key points: (i) Utilizing wavelet transform to perform lossless downsampling of time series. (ii) Achieving cross-band information fusion with a learnable filter. (iii) Using only one shared linear layer or one shallow MLP for sub-series' mapping. We conduct comprehensive experiments, and the results show that SWIFT achieves state-of-the-art (SOTA) performance on multiple datasets, offering a promising method for edge computing and deployment in this task. Moreover, it is noteworthy that the number of parameters in SWIFT-Linear is only 25\% of what it would be with a single-layer linear model for time-domain prediction. Our code is available at https://github.com/LancelotXWX/SWIFT.

Infrared small target detection (IRSTD) is critical for defense and surveillance but remains challenging due to (1) target loss from minimal features, (2) false alarms in cluttered environments, (3) missed detections from low saliency, and (4) high computational costs. To address these issues, we propose TY-RIST, an optimized YOLOv12n architecture that integrates (1) a stride-aware backbone with fine-grained receptive fields, (2) a high-resolution detection head, (3) cascaded coordinate attention blocks, and (4) a branch pruning strategy that reduces computational cost by about 25.5% while marginally improving accuracy and enabling real-time inference. We also incorporate the Normalized Gaussian Wasserstein Distance (NWD) to enhance regression stability. Extensive experiments on four benchmarks and across 20 different models demonstrate state-of-the-art performance, improving mAP at 0.5 IoU by +7.9%, Precision by +3%, and Recall by +10.2%, while achieving up to 123 FPS on a single GPU. Cross-dataset validation on a fifth dataset further confirms strong generalization capability. Additional results and resources are available at https://www.github.com/moured/TY-RIST

Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for real-world deployment. This paper introduces SimpleDeepSearcher, a lightweight yet effective framework that bridges this gap through strategic data engineering rather than complex training paradigms. Our approach synthesizes high-quality training data by simulating realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy that optimizes the diversity and quality of input and output side. Experiments on five benchmarks across diverse domains demonstrate that SFT on only 871 curated samples yields significant improvements over RL-based baselines. Our work establishes SFT as a viable pathway by systematically addressing the data-scarce bottleneck, offering practical insights for efficient deep search systems. Our code is available at https://github.com/RUCAIBox/SimpleDeepSearcher.

Remote Code Execution (RCE) exploits pose a significant threat to AI and ML systems, particularly in GPU-accelerated environments where the computational power of GPUs can be misused for malicious purposes. This paper focuses on RCE attacks leveraging deserialization vulnerabilities and custom layers, such as TensorFlow Lambda layers, which are often overlooked due to the complexity of monitoring GPU workloads. These vulnerabilities enable attackers to execute arbitrary code, blending malicious activity seamlessly into expected model behavior and exploiting GPUs for unauthorized tasks such as cryptocurrency mining. Unlike traditional CPU-based attacks, the parallel processing nature of GPUs and their high resource utilization make runtime detection exceptionally challenging. In this work, we provide a comprehensive examination of RCE exploits targeting GPUs, demonstrating an attack that utilizes these vulnerabilities to deploy a crypto miner on a GPU. We highlight the technical intricacies of such attacks, emphasize their potential for significant financial and computational costs, and propose strategies for mitigation. By shedding light on this underexplored attack vector, we aim to raise awareness and encourage the adoption of robust security measures in GPU-driven AI and ML systems, with an emphasis on static and model scanning as an easier way to detect exploits.

Placenta volume measured from 3D ultrasound (3DUS) images is an important tool for tracking the growth trajectory and is associated with pregnancy outcomes. Manual segmentation is the gold standard, but it is time-consuming and subjective. Although fully automated deep learning algorithms perform well, they do not always yield high-quality results for each case. Interactive segmentation models could address this issue. However, there is limited work on interactive segmentation models for the placenta. Despite their segmentation accuracy, these methods may not be feasible for clinical use as they require relatively large computational power which may be especially prohibitive in low-resource environments, or on mobile devices. In this paper, we propose a lightweight interactive segmentation model aiming for clinical use to interactively segment the placenta from 3DUS images in real-time. The proposed model adopts the segmentation from our fully automated model for initialization and is designed in a human-in-the-loop manner to achieve iterative improvements. The Dice score and normalized surface Dice are used as evaluation metrics. The results show that our model can achieve superior performance in segmentation compared to state-of-the-art models while using significantly fewer parameters. Additionally, the proposed model is much faster for inference and robust to poor initial masks. The code is available at https://github.com/MedICL-VU/PRISM-placenta.

In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiquitous relevance of such settings, decentralized machine learning algorithms have struggled to find equilibria that maximize individual utility while preserving social welfare. In this paper we introduce Learning with Opponent Q-Learning Awareness (LOQA), a novel, decentralized reinforcement learning algorithm tailored to optimizing an agent's individual utility while fostering cooperation among adversaries in partially competitive environments. LOQA assumes the opponent samples actions proportionally to their action-value function Q. Experimental results demonstrate the effectiveness of LOQA at achieving state-of-the-art performance in benchmark scenarios such as the Iterated Prisoner's Dilemma and the Coin Game. LOQA achieves these outcomes with a significantly reduced computational footprint, making it a promising approach for practical multi-agent applications.

Despite the recent success associated with Large Language Models (LLMs), they are notably cost-prohibitive to deploy in resource-constrained environments due to their excessive memory and computational demands. In addition to model parameters, the key-value cache is also stored in GPU memory, growing linearly with batch size and sequence length. As a remedy, recent works have proposed various eviction policies for maintaining the overhead of key-value cache under a given budget. This paper embarks on the efficacy of existing eviction policies in terms of importance score calculation and eviction scope construction. We identify the deficiency of prior policies in these two aspects and introduce RoCo, a robust cache omission policy based on temporal attention scores and robustness measures. Extensive experimentation spanning prefilling and auto-regressive decoding stages validates the superiority of RoCo. Finally, we release EasyKV, a versatile software package dedicated to user-friendly key-value constrained generative inference. Code available at https://github.com/DRSY/EasyKV.

Model-based reinforcement learning is a powerful tool, but collecting data to fit an accurate model of the system can be costly. Exploring an unknown environment in a sample-efficient manner is hence of great importance. However, the complexity of dynamics and the computational limitations of real systems make this task challenging. In this work, we introduce FLEX, an exploration algorithm for nonlinear dynamics based on optimal experimental design. Our policy maximizes the information of the next step and results in an adaptive exploration algorithm, compatible with generic parametric learning models and requiring minimal resources. We test our method on a number of nonlinear environments covering different settings, including time-varying dynamics. Keeping in mind that exploration is intended to serve an exploitation objective, we also test our algorithm on downstream model-based classical control tasks and compare it to other state-of-the-art model-based and model-free approaches. The performance achieved by FLEX is competitive and its computational cost is low.