Daily Papers

Recognizing interactive action plays an important role in human-robot interaction and collaboration. Previous methods use late fusion and co-attention mechanism to capture interactive relations, which have limited learning capability or inefficiency to adapt to more interacting entities. With assumption that priors of each entity are already known, they also lack evaluations on a more general setting addressing the diversity of subjects. To address these problems, we propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Specifically, our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. By extending the entity dimension, ISTs provide better interactive representations. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations. When modeling correlations, a strict entity ordering is usually irrelevant for recognizing interactive actions. To this end, Entity Rearrangement is proposed to eliminate the orderliness in ISTs for interchangeable entities. Extensive experiments on four datasets verify the effectiveness of ISTA-Net by outperforming state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/ISTA-Net

Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision. While most existing methods rely on skeleton sequences--effective in low-light and privacy-sensitive environment--they face two major challenges: 1) learning and effectively exploiting interaction cues from skeletal data, and 2) compensating for the lack of visual information absent in skeletons alone. To address these challenges, we propose skeletal token alignment and rearrangement (STAR) for human-robot and human-human interaction recognition. It learns interaction-specific skeleton features and enriches them using visual cues by aligning skeleton and RGB video representations in a shared latent space. Specifically, STAR consists of three key components. First, we design a skeleton encoder that captures fine-grained interdependencies using Entity Rearrangement (ER) and Interactive Spatiotemporal Tokens (ISTs). Second, we present Visual Interaction Encoding that introduces a Focus on Interactions (FoI) strategy to attend to spatiotemporal regions relevant to interactions in RGB videos. Finally, these representations are aligned via a contrastive learning objective, with a refinement head further refines predictions. During training, STAR leverages both skeleton and RGB video data to learn robust, discriminative interaction representations. At inference time, it operates on skeletons alone, retaining visual-informed benefits while preserving skeleton-only efficiency. Extensive experiments on Chico, HARPER, NTU Mutual 11 and 26 datasets consistently validate our approach by demonstrating superior performance over state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/STAR.

We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

The emergence of neural representations has revolutionized our means for digitally viewing a wide range of 3D scenes, enabling the synthesis of photorealistic images rendered from novel views. Recently, several techniques have been proposed for connecting these low-level representations with the high-level semantics understanding embodied within the scene. These methods elevate the rich semantic understanding from 2D imagery to 3D representations, distilling high-dimensional spatial features onto 3D space. In our work, we are interested in connecting language with a dynamic modeling of the world. We show how to lift spatio-temporal features to a 4D representation based on 3D Gaussian Splatting. This enables an interactive interface where the user can spatiotemporally localize events in the video from text prompts. We demonstrate our system on public 3D video datasets of people and animals performing various actions.

We present TokenDial, a framework for continuous, slider-style attribute control in pretrained text-to-video generation models. While modern generators produce strong holistic videos, they offer limited control over how much an attribute changes (e.g., effect intensity or motion magnitude) without drifting identity, background, or temporal coherence. TokenDial is built on the observation: additive offsets in the intermediate spatiotemporal visual patch-token space form a semantic control direction, where adjusting the offset magnitude yields coherent, predictable edits for both appearance and motion dynamics. We learn attribute-specific token offsets without retraining the backbone, using pretrained understanding signals: semantic direction matching for appearance and motion-magnitude scaling for motion. We demonstrate TokenDial's effectiveness on diverse attributes and prompts, achieving stronger controllability and higher-quality edits than state-of-the-art baselines, supported by extensive quantitative evaluation and human studies.

We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understanding without requiring tracklets, we introduce an auxiliary task that guides Token Mark by leveraging the consistency of the tokens, enabling stable region interpretation across the video. Additionally, we introduce a large-scale region-level video instruction dataset (RegVID-300k). Omni-RGPT achieves state-of-the-art results on image and video-based commonsense reasoning benchmarks while showing strong performance in captioning and referring expression comprehension tasks.

Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic reasoning, they remain coarse in temporal perception: timestamps are encoded only implicitly, frame level features are weak in capturing continuity, and language vision alignment often drifts from the entities of interest. In this paper, we present Grounded VideoDiT, a Video LLM designed to overcome these limitations by introducing three key innovations. First, a Diffusion Temporal Latent (DTL) encoder enhances boundary sensitivity and maintains temporal consistency. Second, object grounded representations explicitly bind query entities to localized visual evidence, strengthening alignment. Third, a mixed token scheme with discrete temporal tokens provides explicit timestamp modeling, enabling fine grained temporal reasoning. Together, these designs equip Grounded VideoDiT with robust grounding capabilities, as validated by state of the art results on Charades STA, NExT GQA, and multiple VideoQA benchmarks.

Large Multimodal Models (LMMs) have become a pivotal research focus in deep learning, demonstrating remarkable capabilities in 3D scene understanding. However, current 3D LMMs employing thousands of spatial tokens for multimodal reasoning suffer from critical inefficiencies: excessive computational overhead and redundant information flows. Unlike 2D VLMs processing single images, 3D LMMs exhibit inherent architectural redundancy due to the heterogeneous mechanisms between spatial tokens and visual tokens. To address this challenge, we propose AdaToken-3D, an adaptive spatial token optimization framework that dynamically prunes redundant tokens through spatial contribution analysis. Our method automatically tailors pruning strategies to different 3D LMM architectures by quantifying token-level information flows via attention pattern mining. Extensive experiments on LLaVA-3D (a 7B parameter 3D-LMM) demonstrate that AdaToken-3D achieves 21\% faster inference speed and 63\% FLOPs reduction while maintaining original task accuracy. Beyond efficiency gains, this work systematically investigates redundancy patterns in multimodal spatial information flows through quantitative token interaction analysis. Our findings reveal that over 60\% of spatial tokens contribute minimally (<5\%) to the final predictions, establishing theoretical foundations for efficient 3D multimodal learning.

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released at https://github.com/Jayce1kk/SpaceVLLM.

Human-centric motion control in video generation remains a critical challenge, particularly when jointly controlling camera movements and human poses in scenarios like the iconic Grammy Glambot moment. While recent video diffusion models have made significant progress, existing approaches struggle with limited motion representations and inadequate integration of camera and human motion controls. In this work, we present TokenMotion, the first DiT-based video diffusion framework that enables fine-grained control over camera motion, human motion, and their joint interaction. We represent camera trajectories and human poses as spatio-temporal tokens to enable local control granularity. Our approach introduces a unified modeling framework utilizing a decouple-and-fuse strategy, bridged by a human-aware dynamic mask that effectively handles the spatially-and-temporally varying nature of combined motion signals. Through extensive experiments, we demonstrate TokenMotion's effectiveness across both text-to-video and image-to-video paradigms, consistently outperforming current state-of-the-art methods in human-centric motion control tasks. Our work represents a significant advancement in controllable video generation, with particular relevance for creative production applications.

Continuous Sign Language Recognition (CSLR) is a crucial task for understanding the languages of deaf communities. Contemporary keypoint-based approaches typically rely on spatio-temporal encoding, where spatial interactions among keypoints are modeled using Graph Convolutional Networks or attention mechanisms, while temporal dynamics are captured using 1D convolutional networks. However, such designs often introduce a large number of parameters in both the encoder and the decoder. This paper introduces a unified spatio-temporal attention network that computes attention scores both spatially (across keypoints) and temporally (within local windows), and aggregates features to produce a local context-aware spatio-temporal representation. The proposed encoder contains approximately 70-80% fewer parameters than existing state-of-the-art models while achieving comparable performance to keypoint-based methods on the Phoenix-14T dataset.

Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often produce results lacking realism and fidelity. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each token. Building on this representation, InterMask utilizes a generative masked modeling framework to collaboratively model the tokens of two interacting individuals. This is achieved by employing a transformer architecture specifically designed to capture complex spatio-temporal inter-dependencies. During training, it randomly masks the motion tokens of both individuals and learns to predict them. For inference, starting from fully masked sequences, it progressively fills in the tokens for both individuals. With its enhanced motion representation, dedicated architecture, and effective learning strategy, InterMask achieves state-of-the-art results, producing high-fidelity and diverse human interactions. It outperforms previous methods, achieving an FID of 5.154 (vs 5.535 of in2IN) on the InterHuman dataset and 0.399 (vs 5.207 of InterGen) on the InterX dataset. Additionally, InterMask seamlessly supports reaction generation without the need for model redesign or fine-tuning.

Vision-Language Models (VLMs) have achieved remarkable success across a range of multimodal tasks; however, their practical deployment is often constrained by high computational costs and prolonged inference times. Since the vision modality typically carries more information than the text modality, compressing visual prompts offers a promising solution to alleviate these challenges. Existing approaches predominantly focus on refining model architectures or directly reducing the number of visual tokens. However, these methods often compromise inference performance due to a lack of consideration for the unique spatial and temporal characteristics of visual data. In this work, we propose a token compression paradigm that operates on both spatial and temporal dimensions. Our approach includes a learning-free, plug-and-play compression pipeline that can be seamlessly integrated into most Multimodal Large Language Model (MLLM) frameworks. By leveraging this method, we enhance the model inference capability while simultaneously reducing its computational cost. Experimental results on the Video-QA task demonstrate the effectiveness of the proposed approach, showcasing significant improvements in efficiency without sacrificing performance.

Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standard approach to video tokenization is to represent a video as a spatiotemporal 3D grid of tokens, each capturing the corresponding local information in the original signal. This requires the downstream model that consumes the tokens, e.g., a text-to-video model, to learn to predict all low-level details "pixel-by-pixel" irrespective of the video's inherent complexity, leading to high learning complexity. We present VideoFlexTok, which represents videos with a variable-length sequence of tokens structured in a coarse-to-fine manner -- where the first tokens (emergently) capture abstract information, such as semantics and motion, and later tokens add fine-grained details. The generative flow decoder enables realistic video reconstructions from any token count. This representation structure allows adapting the token count according to downstream needs and encoding videos longer than the baselines with the same budget. We evaluate VideoFlexTok on class- and text-to-video generative tasks and show that it leads to more efficient training compared to 3D grid tokens, e.g., achieving comparable generation quality (gFVD and ViCLIP Score) with a 5x smaller model (1.1B vs 5.2B). Finally, we demonstrate how VideoFlexTok can enable long video generation without prohibitive computational cost by training a text-to-video model on 10-second 81-frame videos with only 672 tokens, 8x fewer than a comparable 3D grid tokenizer.

Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space. However, we demonstrate that treating all image-tokens equally as done by S4 model can adversely affect its efficiency and accuracy. To address this limitation, we present a novel Selective S4 (i.e., S5) model that employs a lightweight mask generator to adaptively select informative image tokens resulting in more efficient and accurate modeling of long-term spatiotemporal dependencies in videos. Unlike previous mask-based token reduction methods used in transformers, our S5 model avoids the dense self-attention calculation by making use of the guidance of the momentum-updated S4 model. This enables our model to efficiently discard less informative tokens and adapt to various long-form video understanding tasks more effectively. However, as is the case for most token reduction methods, the informative image tokens could be dropped incorrectly. To improve the robustness and the temporal horizon of our model, we propose a novel long-short masked contrastive learning (LSMCL) approach that enables our model to predict longer temporal context using shorter input videos. We present extensive comparative results using three challenging long-form video understanding datasets (LVU, COIN and Breakfast), demonstrating that our approach consistently outperforms the previous state-of-the-art S4 model by up to 9.6% accuracy while reducing its memory footprint by 23%.

Spatio-temporal video grounding (STVG) aims at localizing the spatio-temporal tube of a video, as specified by the input text query. In this paper, we utilize multimodal large language models (MLLMs) to explore a zero-shot solution in STVG. We reveal two key insights about MLLMs: (1) MLLMs tend to dynamically assign special tokens, referred to as grounding tokens, for grounding the text query; and (2) MLLMs often suffer from suboptimal grounding due to the inability to fully integrate the cues in the text query (e.g., attributes, actions) for inference. Based on these insights, we propose a MLLM-based zero-shot framework for STVG, which includes novel decomposed spatio-temporal highlighting (DSTH) and temporal-augmented assembling (TAS) strategies to unleash the reasoning ability of MLLMs. The DSTH strategy first decouples the original query into attribute and action sub-queries for inquiring the existence of the target both spatially and temporally. It then uses a novel logit-guided re-attention (LRA) module to learn latent variables as spatial and temporal prompts, by regularizing token predictions for each sub-query. These prompts highlight attribute and action cues, respectively, directing the model's attention to reliable spatial and temporal related visual regions. In addition, as the spatial grounding by the attribute sub-query should be temporally consistent, we introduce the TAS strategy to assemble the predictions using the original video frames and the temporal-augmented frames as inputs to help improve temporal consistency. We evaluate our method on various MLLMs, and show that it outperforms SOTA methods on three common STVG benchmarks. The code will be available at https://github.com/zaiquanyang/LLaVA_Next_STVG.

Predicting human mobility is inherently challenging due to complex long-range dependencies and multi-scale periodic behaviors. To address this, we introduce RHYTHM (Reasoning with Hierarchical Temporal Tokenization for Human Mobility), a unified framework that leverages large language models (LLMs) as general-purpose spatio-temporal predictors and trajectory reasoners. Methodologically, RHYTHM employs temporal tokenization to partition each trajectory into daily segments and encode them as discrete tokens with hierarchical attention that captures both daily and weekly dependencies, thereby significantly reducing the sequence length while preserving cyclical information. Additionally, we enrich token representations by adding pre-computed prompt embeddings for trajectory segments and prediction targets via a frozen LLM, and feeding these combined embeddings back into the LLM backbone to capture complex interdependencies. Computationally, RHYTHM freezes the pretrained LLM's backbone to reduce attention complexity and memory cost. We evaluate our model against state-of-the-art methods using three real-world datasets. Notably, RHYTHM achieves a 2.4% improvement in overall accuracy, a 5.0% increase on weekends, and a 24.6% reduction in training time. Code is publicly available at https://github.com/he-h/rhythm.

Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and task-agnostic. We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective, dynamically adapting its token granularity to semantic complexity, independent of video duration. TrajTok contains a unified segmenter that performs implicit clustering over pixels in both space and time to directly produce object trajectories in a single forward pass. By prioritizing downstream adaptability over pixel-perfect segmentation fidelity, TrajTok is lightweight and efficient, yet empirically improves video understanding performance. With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods. TrajTok also proves to be a versatile component beyond its role as a tokenizer. We show that it can be seamlessly integrated as either a probing head for pretrained visual features (TrajAdapter) or an alignment connector in vision-language models (TrajVLM) with especially strong performance in long-video reasoning.

We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames. BLIP-3-Video takes advantage of the 'temporal encoder' in addition to the conventional visual tokenizer, which maps a sequence of tokens over multiple frames into a compact set of visual tokens. This enables BLIP3-Video to use much fewer visual tokens than its competing models (e.g., 32 vs. 4608 tokens). We explore different types of temporal encoders, including learnable spatio-temporal pooling as well as sequential models like Token Turing Machines. We experimentally confirm that BLIP-3-Video obtains video question-answering accuracies comparable to much larger state-of-the-art models (e.g., 34B), while being much smaller (i.e., 4B) and more efficient by using fewer visual tokens. The project website is at https://www.salesforceairesearch.com/opensource/xGen-MM-Vid/index.html

Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ignore some of the events or fail to arrange them in the correct order. To address this limitation, we present MinT, a multi-event video generator with temporal control. Our key insight is to bind each event to a specific period in the generated video, which allows the model to focus on one event at a time. To enable time-aware interactions between event captions and video tokens, we design a time-based positional encoding method, dubbed ReRoPE. This encoding helps to guide the cross-attention operation. By fine-tuning a pre-trained video diffusion transformer on temporally grounded data, our approach produces coherent videos with smoothly connected events. For the first time in the literature, our model offers control over the timing of events in generated videos. Extensive experiments demonstrate that MinT outperforms existing open-source models by a large margin.

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relevant to actor motions from other frames, and drop out the remaining tokens in this clip. Second, we refine scene context by leveraging remaining tokens for better recognizing actor identities. The region of interest (RoI) in our action detector is expanded into temporal domain. The captured spatiotemporal actor identity representations are refined via scene context in a decoder with the attention mechanism. These two designs make our EVAD efficient while maintaining accuracy, which is validated on three benchmark datasets (i.e., AVA, UCF101-24, JHMDB). Compared to the vanilla ViT backbone, our EVAD reduces the overall GFLOPs by 43% and improves real-time inference speed by 40% with no performance degradation. Moreover, even at similar computational costs, our EVAD can improve the performance by 1.1 mAP with higher resolution inputs. Code is available at https://github.com/MCG-NJU/EVAD.

Event cameras capture dynamic scenes with exceptional temporal fidelity by representing them as a continuous stream of microsecond resolution events. Each individual event, however, only carries minimal semantic value, merely signaling a localized brightness change. To derive meaningful signals, downstream algorithms need to quickly integrate cues from a potentially massive torrent of low-information events. Current architectures, however, are easily overwhelmed, struggling to balance capturing fine-grained temporal dynamics and maintaining a manageable data throughput. This paper proposes a framework to re-tokenize event streams into a small set of highly informative neural events, each representing a local spatio-temporal context window with a discrete learnable code. Every time this code flips, a neural event is triggered, yielding a highly compressed data stream. We demonstrate that, across object detection and classification, networks trained on neural events are on par or surpass the performance of state-of-the-art approaches while reducing the event rate by a factor of 2.0.

Spatio-temporal action detection encompasses the tasks of localizing and classifying individual actions within a video. Recent works aim to enhance this process by incorporating interaction modeling, which captures the relationship between people and their surrounding context. However, these approaches have primarily focused on fully-supervised learning, and the current limitation lies in the lack of generalization capability to recognize unseen action categories. In this paper, we aim to adapt the pretrained image-language models to detect unseen actions. To this end, we propose a method which can effectively leverage the rich knowledge of visual-language models to perform Person-Context Interaction. Meanwhile, our Context Prompting module will utilize contextual information to prompt labels, thereby enhancing the generation of more representative text features. Moreover, to address the challenge of recognizing distinct actions by multiple people at the same timestamp, we design the Interest Token Spotting mechanism which employs pretrained visual knowledge to find each person's interest context tokens, and then these tokens will be used for prompting to generate text features tailored to each individual. To evaluate the ability to detect unseen actions, we propose a comprehensive benchmark on J-HMDB, UCF101-24, and AVA datasets. The experiments show that our method achieves superior results compared to previous approaches and can be further extended to multi-action videos, bringing it closer to real-world applications. The code and data can be found in https://webber2933.github.io/ST-CLIP-project-page.

Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to focus more on the semantic content of videos, often overlooking emotional stimuli. Hence, most existing MLLMs fall short in estimating viewers' emotional reactions and providing plausible explanations. To address this issue, we propose StimuVAR, a spatiotemporal Stimuli-aware framework for Video Affective Reasoning (VAR) with MLLMs. StimuVAR incorporates a two-level stimuli-aware mechanism: frame-level awareness and token-level awareness. Frame-level awareness involves sampling video frames with events that are most likely to evoke viewers' emotions. Token-level awareness performs tube selection in the token space to make the MLLM concentrate on emotion-triggered spatiotemporal regions. Furthermore, we create VAR instruction data to perform affective training, steering MLLMs' reasoning strengths towards emotional focus and thereby enhancing their affective reasoning ability. To thoroughly assess the effectiveness of VAR, we provide a comprehensive evaluation protocol with extensive metrics. StimuVAR is the first MLLM-based method for viewer-centered VAR. Experiments demonstrate its superiority in understanding viewers' emotional responses to videos and providing coherent and insightful explanations.

Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harmony between the quantity and diversity of tools. To better control the tool invocation sequence and avoid toolchain shortcut issues, we propose a Spatiotemporal Reasoning Framework (STAR) that strategically schedules temporal and spatial tools, thereby progressively localizing the key area in the video. Our STAR framework enhances GPT-4o using lightweight tools, achieving an 8.2% gain on VideoMME and 4.6% on LongVideoBench. We believe that our proposed Video Toolkit and STAR framework make an important step towards building autonomous and intelligent video analysis assistants. The code is publicly available at https://github.com/fansunqi/VideoTool.

We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous and spatially sparse events, our goal is to discover an event representation that preserves these properties. Prior works have represented events as frames or as voxels. However, while these representations yield high accuracy, both frames and voxels are synchronous and decrease the spatial sparsity. Spiking Patches gives the means to preserve the unique properties of event cameras and we show in our experiments that this comes without sacrificing accuracy. We evaluate our tokenizer using a GNN, PCN, and a Transformer on gesture recognition and object detection. Tokens from Spiking Patches yield inference times that are up to 3.4x faster than voxel-based tokens and up to 10.4x faster than frames. We achieve this while matching their accuracy and even surpassing in some cases with absolute improvements up to 3.8 for gesture recognition and up to 1.4 for object detection. Thus, tokenization constitutes a novel direction in event-based vision and marks a step towards methods that preserve the properties of event cameras.

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a appropriate prediction unit? To address this, we present VideoAR, a unified framework that supports a spectrum of prediction units including full frames, key-detail frames, multiscale refinements, and spatiotemporal cubes. Among these designs, we find model video generation using spatiotemporal cubes as prediction units, which allows autoregressive models to operate across both spatial and temporal dimensions simultaneously. This approach eliminates the assumption that frames are the natural atomic units for video autoregression. We evaluate VideoAR across diverse prediction strategies, finding that cube-based prediction consistently delivers superior quality, speed, and temporal coherence. By removing the frame-by-frame constraint, our video generator surpasses state-of-the-art baselines on VBench while achieving faster inference and enabling seamless scaling to minute-long sequences. We hope this work will motivate rethinking sequence decomposition in video and other spatiotemporal domains.

Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational overhead from massive audio and video tokens. Token reduction, while extensively explored for video-only LLMs, is insufficient for the audio-visual domain, as these unimodal methods cannot leverage audio-visual cross-modal synergies. Furthermore, the distinct and dynamic information densities of audio and video render static budgets per modality suboptimal. How to perform token reduction on a joint audio-visual stream thus remains an unaddressed bottleneck. To fill this gap, we introduce EchoingPixels, a framework inspired by the coexistence and interaction of visuals and sound in real-world scenes. The core of our framework is the Cross-Modal Semantic Sieve (CS2), a module enabling early audio-visual interaction. Instead of compressing modalities independently, CS2 co-attends to the joint multimodal stream and reduces tokens from an entire combined pool of audio-visual tokens rather than using fixed budgets per modality. This single-pool approach allows it to adaptively allocate the token budget across both modalities and dynamically identify salient tokens in concert. To ensure this aggressive reduction preserves the vital temporal modeling capability, we co-design a Synchronization-Augmented RoPE (Sync-RoPE) to maintain critical temporal relationships for the sparsely selected tokens. Extensive experiments demonstrate that EchoingPixels achieves performance comparable to strong baselines using only 5-20% of the original tokens, with a 2-3x speedup and memory reduction.

We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at https://github.com/facebookresearch/SlowFast

In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting strategies to obtain visual tokens and processing a large number of densely sampled patches for attention, our approach learns to mine important tokens in visual data. This results in efficiently and effectively finding a few important visual tokens and enables modeling of pairwise attention between such tokens, over a longer temporal horizon for videos, or the spatial content in images. Our experiments demonstrate strong performance on several challenging benchmarks for both image and video recognition tasks. Importantly, due to our tokens being adaptive, we accomplish competitive results at significantly reduced compute amount. We obtain comparable results to the state-of-the-arts on ImageNet while being computationally more efficient. We also confirm the effectiveness of the approach on multiple video datasets, including Kinetics-400, Kinetics-600, Charades, and AViD. The code is available at: https://github.com/google-research/scenic/tree/main/scenic/projects/token_learner

The rapid growth of online video platforms, particularly live streaming services, has created an urgent need for real-time video understanding systems. These systems must process continuous video streams and respond to user queries instantaneously, presenting unique challenges for current Video Large Language Models (VideoLLMs). While existing VideoLLMs excel at processing complete videos, they face significant limitations in streaming scenarios due to their inability to handle dense, redundant frames efficiently. We introduce TimeChat-Online, a novel online VideoLLM that revolutionizes real-time video interaction. At its core lies our innovative Differential Token Drop (DTD) module, which addresses the fundamental challenge of visual redundancy in streaming videos. Drawing inspiration from human visual perception's Change Blindness phenomenon, DTD preserves meaningful temporal changes while filtering out static, redundant content between frames. Remarkably, our experiments demonstrate that DTD achieves an 82.8% reduction in video tokens while maintaining 98% performance on StreamingBench, revealing that over 80% of visual content in streaming videos is naturally redundant without requiring language guidance. To enable seamless real-time interaction, we present TimeChat-Online-139K, a comprehensive streaming video dataset featuring diverse interaction patterns including backward-tracing, current-perception, and future-responding scenarios. TimeChat-Online's unique Proactive Response capability, naturally achieved through continuous monitoring of video scene transitions via DTD, sets it apart from conventional approaches. Our extensive evaluation demonstrates TimeChat-Online's superior performance on streaming benchmarks (StreamingBench and OvOBench) and maintaining competitive results on long-form video tasks such as Video-MME and MLVU.

The growing interest in embodied agents increases the demand for spatiotemporal video understanding, yet existing benchmarks largely emphasize extractive reasoning, where answers can be explicitly presented within spatiotemporal events. It remains unclear whether multimodal large language models can instead perform abstractive spatiotemporal reasoning, which requires integrating observations over time, combining dispersed cues, and inferring implicit spatial and contextual structure. To address this gap, we formalize abstractive spatiotemporal reasoning from videos by introducing a structured evaluation taxonomy that systematically targets its core dimensions and construct a controllable, scenario-driven synthetic egocentric video dataset tailored to evaluate abstractive spatiotemporal reasoning capabilities, spanning object-, room-, and floor-plan-level scenarios. Based on this framework, we present VAEX-BENCH, a benchmark comprising five abstractive reasoning tasks together with their extractive counterparts. Our extensive experiments compare the performance of state-of-the-art MLLMs under extractive and abstractive settings, exposing their limitations on abstractive tasks and providing a fine-grained analysis of the underlying bottlenecks. The dataset will be released soon.

Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration frameworks usually compress spatial and temporal redundancy independently, which overlooks the spatiotemporal relationships, thereby leading to suboptimal spatiotemporal compression. The highly correlated visual features are likely to change in spatial position, scale, orientation, and other attributes over time due to the dynamic nature of video. Building on this insight, we introduce FlashVID, a training-free inference acceleration framework for VLLMs. Specifically, FlashVID utilizes Attention and Diversity-based Token Selection (ADTS) to select the most representative tokens for basic video representation, then applies Tree-based Spatiotemporal Token Merging (TSTM) for fine-grained spatiotemporal redundancy elimination. Extensive experiments conducted on three representative VLLMs across five video understanding benchmarks demonstrate the effectiveness and generalization of our method. Notably, by retaining only 10% of visual tokens, FlashVID preserves 99.1% of the performance of LLaVA-OneVision. Consequently, FlashVID can serve as a training-free and plug-and-play module for extending long video frames, which enables a 10x increase in video frame input to Qwen2.5-VL, resulting in a relative improvement of 8.6% within the same computational budget. Code is available at https://github.com/Fanziyang-v/FlashVID.

Recently there has been a lot of progress in text-to-video generation, with state-of-the-art models being capable of generating high quality, realistic videos. However, these models lack the capability for users to interactively control and generate videos, which can potentially unlock new areas of application. As a first step towards this goal, we tackle the problem of endowing diffusion-based video generation models with interactive spatio-temporal control over their output. To this end, we take inspiration from the recent advances in segmentation literature to propose a novel spatio-temporal masked attention module - Peekaboo. This module is a training-free, no-inference-overhead addition to off-the-shelf video generation models which enables spatio-temporal control. We also propose an evaluation benchmark for the interactive video generation task. Through extensive qualitative and quantitative evaluation, we establish that Peekaboo enables control video generation and even obtains a gain of upto 3.8x in mIoU over baseline models.

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400) and exhibit unsatisfactory out-of-the-box representations. We argue that it is due to the fact that they only capture pixel-level knowledge rather than spatiotemporal semantics, which hinders further progress in video understanding. Inspired by the great success of image-text pre-training (e.g., CLIP), we take the first step to exploit language semantics to boost transferable spatiotemporal representation learning. We introduce a new pretext task, Turning to Video for Transcript Sorting (TVTS), which sorts shuffled ASR scripts by attending to learned video representations. We do not rely on descriptive captions and learn purely from video, i.e., leveraging the natural transcribed speech knowledge to provide noisy but useful semantics over time. Our method enforces the vision model to contextualize what is happening over time so that it can re-organize the narrative transcripts, and can seamlessly apply to large-scale uncurated video data in the real world. Our method demonstrates strong out-of-the-box spatiotemporal representations on diverse benchmarks, e.g., +13.6% gains over VideoMAE on SSV2 via linear probing. The code is available at https://github.com/TencentARC/TVTS.

We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we introduce Temporal Contextualization (TC), a layer-wise temporal information infusion mechanism for videos, which 1) extracts core information from each frame, 2) connects relevant information across frames for the summarization into context tokens, and 3) leverages the context tokens for feature encoding. Furthermore, the Video-conditional Prompting (VP) module processes context tokens to generate informative prompts in the text modality. Extensive experiments in zero-shot, few-shot, base-to-novel, and fully-supervised action recognition validate the effectiveness of our model. Ablation studies for TC and VP support our design choices. Our project page with the source code is available at https://github.com/naver-ai/tc-clip

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In this paper, we propose TokensGen, a novel two-stage framework that leverages condensed tokens to address these issues. Our method decomposes long video generation into three core tasks: (1) inner-clip semantic control, (2) long-term consistency control, and (3) inter-clip smooth transition. First, we train To2V (Token-to-Video), a short video diffusion model guided by text and video tokens, with a Video Tokenizer that condenses short clips into semantically rich tokens. Second, we introduce T2To (Text-to-Token), a video token diffusion transformer that generates all tokens at once, ensuring global consistency across clips. Finally, during inference, an adaptive FIFO-Diffusion strategy seamlessly connects adjacent clips, reducing boundary artifacts and enhancing smooth transitions. Experimental results demonstrate that our approach significantly enhances long-term temporal and content coherence without incurring prohibitive computational overhead. By leveraging condensed tokens and pre-trained short video models, our method provides a scalable, modular solution for long video generation, opening new possibilities for storytelling, cinematic production, and immersive simulations. Please see our project page at https://vicky0522.github.io/tokensgen-webpage/ .

Embodied Conversational Agents (ECAs) aim to emulate human face-to-face interaction through speech, gestures, and facial expressions. Current large language model (LLM)-based conversational agents lack embodiment and the expressive gestures essential for natural interaction. Existing solutions for ECAs often produce rigid, low-diversity motions, that are unsuitable for human-like interaction. Alternatively, generative methods for co-speech gesture synthesis yield natural body gestures but depend on future speech context and require long run-times. To bridge this gap, we present MIBURI, the first online, causal framework for generating expressive full-body gestures and facial expressions synchronized with real-time spoken dialogue. We employ body-part aware gesture codecs that encode hierarchical motion details into multi-level discrete tokens. These tokens are then autoregressively generated by a two-dimensional causal framework conditioned on LLM-based speech-text embeddings, modeling both temporal dynamics and part-level motion hierarchy in real time. Further, we introduce auxiliary objectives to encourage expressive and diverse gestures while preventing convergence to static poses. Comparative evaluations demonstrate that our causal and real-time approach produces natural and contextually aligned gestures against recent baselines. We urge the reader to explore demo videos on https://vcai.mpi-inf.mpg.de/projects/MIBURI/.

Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for long-form videos. These videos contain massive visual tokens due to their inherent 3D properties and spatiotemporal redundancy, making it challenging to capture complex temporal and spatial relationships. To tackle this issue, we propose an efficient method called TEmporal-Spatial Token Aggregation (TESTA). TESTA condenses video semantics by adaptively aggregating similar frames, as well as similar patches within each frame. TESTA can reduce the number of visual tokens by 75% and thus accelerate video encoding. Building upon TESTA, we introduce a pre-trained video-language model equipped with a divided space-time token aggregation module in each video encoder block. We evaluate our model on five datasets for paragraph-to-video retrieval and long-form VideoQA tasks. Experimental results show that TESTA improves computing efficiency by 1.7 times, and achieves significant performance gains from its scalability in processing longer input frames, e.g., +13.7 R@1 on QuerYD and +6.5 R@1 on Condensed Movie.

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value caching to accumulate frame-level information over time, but use a limited number of tokens per frame, leading to the loss of fine-grained visual details. In this work, we propose scaling the token budget to enable more granular spatiotemporal understanding and reasoning. First, we find that current methods are ill-equipped to handle dense streams: their feature encoding causes query-frame similarity scores to increase over time, biasing retrieval toward later frames. To address this, we introduce an adaptive selection strategy that reduces token redundancy while preserving local spatiotemporal information. We further propose a training-free retrieval mixture-of-experts that leverages external models to better identify relevant frames. Our method, MemStream, achieves +8.0% on CG-Bench, +8.5% on LVBench, and +2.4% on VideoMME (Long) over ReKV with Qwen2.5-VL-7B.

Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free spatio-temporal token merging method, named STTM. Our key insight is to exploit local spatial and temporal redundancy in video data which has been overlooked in prior work. STTM first transforms each frame into multi-granular spatial tokens using a coarse-to-fine search over a quadtree structure, then performs directed pairwise merging across the temporal dimension. This decomposed merging approach outperforms existing token reduction methods across six video QA benchmarks. Notably, STTM achieves a 2times speed-up with only a 0.5% accuracy drop under a 50% token budget, and a 3times speed-up with just a 2% drop under a 30% budget. Moreover, STTM is query-agnostic, allowing KV cache reuse across different questions for the same video. The project page is available at https://www.jshyun.me/projects/sttm.

Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long video sequences lead current video LLMs (Vid-LLMs) to employ compression strategies at both the inter-frame level (e.g., uniform sampling of video frames) and intra-frame level (e.g., condensing all visual tokens of each frame into a limited number). However, this approach often neglects the uneven temporal distribution of critical information across frames, risking the omission of keyframes that contain essential temporal and semantic details. To tackle these challenges, we propose KFFocus, a method designed to efficiently compress video tokens and emphasize the informative context present within video frames. We substitute uniform sampling with a refined approach inspired by classic video compression principles to identify and capture keyframes based on their temporal redundancy. By assigning varying condensation ratios to frames based on their contextual relevance, KFFocus efficiently reduces token redundancy while preserving informative content details. Additionally, we introduce a spatiotemporal modeling module that encodes both the temporal relationships between video frames and the spatial structure within each frame, thus providing Vid-LLMs with a nuanced understanding of spatial-temporal dynamics. Extensive experiments on widely recognized video understanding benchmarks, especially long video scenarios, demonstrate that KFFocus significantly outperforms existing methods, achieving substantial computational efficiency and enhanced accuracy.

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing high-performance models usually process images and videos separately with different token compression strategies, limiting the capabilities of combining images and videos. To this end, we extend each image into a "static" video and introduce a unified token compression strategy called Progressive Visual Token Compression (PVC), where the tokens of each frame are progressively encoded and adaptively compressed to supplement the information not extracted from previous frames. Video tokens are efficiently compressed with exploiting the inherent temporal redundancy. Images are repeated as static videos, and the spatial details can be gradually supplemented in multiple frames. PVC unifies the token compressing of images and videos. With a limited number of tokens per frame (64 tokens by default), spatial details and temporal changes can still be preserved. Experiments show that our model achieves state-of-the-art performance across various video understanding benchmarks, including long video tasks and fine-grained short video tasks. Meanwhile, our unified token compression strategy incurs no performance loss on image benchmarks, particularly in detail-sensitive tasks.

Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Specifically, visual tokens exhibit significantly stronger correlations with their spatially or temporally adjacent tokens compared to those that are distant. In this paper, we propose Neighboring Autoregressive Modeling (NAR), a novel paradigm that formulates autoregressive visual generation as a progressive outpainting procedure, following a near-to-far ``next-neighbor prediction" mechanism. Starting from an initial token, the remaining tokens are decoded in ascending order of their Manhattan distance from the initial token in the spatial-temporal space, progressively expanding the boundary of the decoded region. To enable parallel prediction of multiple adjacent tokens in the spatial-temporal space, we introduce a set of dimension-oriented decoding heads, each predicting the next token along a mutually orthogonal dimension. During inference, all tokens adjacent to the decoded tokens are processed in parallel, substantially reducing the model forward steps for generation. Experiments on ImageNet256times 256 and UCF101 demonstrate that NAR achieves 2.4times and 8.6times higher throughput respectively, while obtaining superior FID/FVD scores for both image and video generation tasks compared to the PAR-4X approach. When evaluating on text-to-image generation benchmark GenEval, NAR with 0.8B parameters outperforms Chameleon-7B while using merely 0.4 of the training data. Code is available at https://github.com/ThisisBillhe/NAR.

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal localization and struggle with videos of varying lengths. We introduce TimeMarker, a versatile Video-LLM designed for high-quality dialogue based on video content, emphasizing temporal localization. TimeMarker integrates Temporal Separator Tokens to enhance temporal awareness, accurately marking specific moments within videos. It employs the AnyLength mechanism for dynamic frame sampling and adaptive token merging, enabling effective handling of both short and long videos. Additionally, TimeMarker utilizes diverse datasets, including further transformed temporal-related video QA datasets, to bolster its temporal understanding capabilities. Image and interleaved data are also employed to further enhance the model's semantic perception ability. Evaluations demonstrate that TimeMarker achieves state-of-the-art performance across multiple benchmarks, excelling in both short and long video categories. Our project page is at https://github.com/TimeMarker-LLM/TimeMarker/.

Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial intelligence. The core challenge is not simply longer context windows but how spatial information is selected, organized, and retained over time. In this paper, we propose Spatial-TTT towards streaming visual-based spatial intelligence with test-time training (TTT), which adapts a subset of parameters (fast weights) to capture and organize spatial evidence over long-horizon scene videos. Specifically, we design a hybrid architecture and adopt large-chunk updates parallel with sliding-window attention for efficient spatial video processing. To further promote spatial awareness, we introduce a spatial-predictive mechanism applied to TTT layers with 3D spatiotemporal convolution, which encourages the model to capture geometric correspondence and temporal continuity across frames. Beyond architecture design, we construct a dataset with dense 3D spatial descriptions, which guides the model to update its fast weights to memorize and organize global 3D spatial signals in a structured manner. Extensive experiments demonstrate that Spatial-TTT improves long-horizon spatial understanding and achieves state-of-the-art performance on video spatial benchmarks. Project page: https://liuff19.github.io/Spatial-TTT.

Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present TimeBlind, a diagnostic benchmark for compositional spatio-temporal understanding. Inspired by cognitive science, TimeBlind categorizes fine-grained temporal understanding into three levels: recognizing atomic events, characterizing event properties, and reasoning about event interdependencies. Unlike benchmarks that conflate recognition with temporal reasoning, TimeBlind leverages a minimal-pairs paradigm: video pairs share identical static visual content but differ solely in temporal structure, utilizing complementary questions to neutralize language priors. Evaluating over 20 state-of-the-art MLLMs (e.g., GPT-5, Gemini 3 Pro) on 600 curated instances (2400 video-question pairs), reveals that the Instance Accuracy (correctly distinguishing both videos in a pair) of the best performing MLLM is only 48.2%, far below the human performance (98.2%). These results demonstrate that even frontier models rely heavily on static visual shortcuts rather than genuine temporal logic, positioning TimeBlind as a vital diagnostic tool for next-generation video understanding. Dataset and code are available at https://baiqi-li.github.io/timeblind_project/ .

Precise geocoding and time normalization for text requires that location and time phrases be identified. Many state-of-the-art geoparsers and temporal parsers suffer from low recall. Categories commonly missed by parsers are: nouns used in a non- spatiotemporal sense, adjectival and adverbial phrases, prepositional phrases, and numerical phrases. We collected and annotated data set by querying commercial web searches API with such spatiotemporal expressions as were missed by state-of-the- art parsers. Due to the high cost of sentence annotation, active learning was used to label training data, and a new strategy was designed to better select training examples to reduce labeling cost. For the learning algorithm, we applied an average perceptron trained Featurized Hidden Markov Model (FHMM). Five FHMM instances were used to create an ensemble, with the output phrase selected by voting. Our ensemble model was tested on a range of sequential labeling tasks, and has shown competitive performance. Our contributions include (1) an new dataset annotated with named entities and expanded spatiotemporal expressions; (2) a comparison of inference algorithms for ensemble models showing the superior accuracy of Belief Propagation over Viterbi Decoding; (3) a new example re-weighting method for active ensemble learning that 'memorizes' the latest examples trained; (4) a spatiotemporal parser that jointly recognizes expanded spatiotemporal expressions as well as named entities.

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order (e.g., raster scan). However, we show that spatial tokens lack the recursive structure inherent to languages, hence form an impossible language for LLM to master. In this paper, we build a proper visual language by leveraging diffusion timesteps to learn discrete, recursive visual tokens. Our proposed tokens recursively compensate for the progressive attribute loss in noisy images as timesteps increase, enabling the diffusion model to reconstruct the original image at any timestep. This approach allows us to effectively integrate the strengths of LLMs in autoregressive reasoning and diffusion models in precise image generation, achieving seamless multimodal comprehension and generation within a unified framework. Extensive experiments show that we achieve superior performance for multimodal comprehension and generation simultaneously compared with other MLLMs. Project Page: https://DDT-LLaMA.github.io/.

Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain gap between language and vision tokens while generation. Addressing these challenges requires an effective video tokenizer that can efficiently encode video data while preserving essential semantic and spatiotemporal information, serving as a critical bridge between text and vision. Inspired by the observation in VQ-VAE-2 and workflows of traditional animation, we propose HiTVideo for text-to-video generation with hierarchical tokenizers. It utilizes a 3D causal VAE with a multi-layer discrete token framework, encoding video content into hierarchically structured codebooks. Higher layers capture semantic information with higher compression, while lower layers focus on fine-grained spatiotemporal details, striking a balance between compression efficiency and reconstruction quality. Our approach efficiently encodes longer video sequences (e.g., 8 seconds, 64 frames), reducing bits per pixel (bpp) by approximately 70\% compared to baseline tokenizers, while maintaining competitive reconstruction quality. We explore the trade-offs between compression and reconstruction, while emphasizing the advantages of high-compressed semantic tokens in text-to-video tasks. HiTVideo aims to address the potential limitations of existing video tokenizers in text-to-video generation tasks, striving for higher compression ratios and simplify LLMs modeling under language guidance, offering a scalable and promising framework for advancing text to video generation. Demo page: https://ziqinzhou66.github.io/project/HiTVideo.

Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight approach enables pixel-level control of an object's position with one token or its bounding box with two, all without requiring architectural changes or bespoke attention masking. The MetaPoint tokens are designed to be compositional, serving as spatial primitives. This allows a planner agent to decompose a high-level user request into a structured sequence of primitives for the generator. By providing a simple, precise, and scalable building block for spatial control, MetaPoint unlocks more powerful compositional generative agents and enables intuitive, interactive editing systems.

In this paper, we present LLaVA-Scissor, a training-free token compression strategy designed for video multimodal large language models. Previous methods mostly attempt to compress tokens based on attention scores, but fail to effectively capture all semantic regions and often lead to token redundancy. Differently, we propose to leverage the Semantic Connected Components (SCC) approach that assigns tokens to distinct semantic regions within the token set, ensuring comprehensive semantic coverage. The outcome is a two-step spatio-temporal token compression strategy that utilizes SCC in both spatial and temporal domains. This strategy can effectively compress tokens by representing the entire video with a set of non-overlapping semantic tokens. We conduct extensive evaluations of the token compression capabilities of LLaVA-Scissor across diverse video understanding benchmarks, including video question answering, long video understanding, and comprehensive multi-choices benchmarks. Experimental results show that the proposed LLaVA-Scissor outperforms other token compression methods, achieving superior performance in various video understanding benchmarks, particularly at low token retention ratios. Project page: https://github.com/HumanMLLM/LLaVA-Scissor.

The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video intERaction Bench (RIVER Bench), designed for evaluating online video comprehension. RIVER Bench introduces a novel framework comprising Retrospective Memory, Live-Perception, and Proactive Anticipation tasks, closely mimicking interactive dialogues rather than responding to entire videos at once. We conducted detailed annotations using videos from diverse sources and varying lengths, and precisely defined the real-time interactive format. Evaluations across various model categories reveal that while offline models perform well in single question-answering tasks, they struggle with real-time processing. Addressing the limitations of existing models in online video interaction, especially their deficiencies in long-term memory and future perception, we proposed a general improvement method that enables models to interact with users more flexibly in real time. We believe this work will significantly advance the development of real-time interactive video understanding models and inspire future research in this emerging field. Datasets and code are publicly available at https://github.com/OpenGVLab/RIVER.

Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body regions such as body, legs and hands separately, which fail to capture the spatial interactions between them and result in unnatural and disjointed movements. Additionally, their autoregressive/diffusion-based pipelines show slow generation speed due to dozens of inference steps. To address these two challenges, we propose GestureLSM, a flow-matching-based approach for Co-Speech Gesture Generation with spatial-temporal modeling. Our method i) explicitly model the interaction of tokenized body regions through spatial and temporal attention, for generating coherent full-body gestures. ii) introduce the flow matching to enable more efficient sampling by explicitly modeling the latent velocity space. To overcome the suboptimal performance of flow matching baseline, we propose latent shortcut learning and beta distribution time stamp sampling during training to enhance gesture synthesis quality and accelerate inference. Combining the spatial-temporal modeling and improved flow matching-based framework, GestureLSM achieves state-of-the-art performance on BEAT2 while significantly reducing inference time compared to existing methods, highlighting its potential for enhancing digital humans and embodied agents in real-world applications. Project Page: https://andypinxinliu.github.io/GestureLSM

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive video generation. Existing autoregressive video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive latency due to next-token decoding. In this paper, we introduce Lumos-1, an autoregressive video generator that retains the LLM architecture with minimal architectural modifications. To inject spatiotemporal correlations in LLMs, we identify the efficacy of incorporating 3D RoPE and diagnose its imbalanced frequency spectrum ranges. Therefore, we propose MM-RoPE, a RoPE scheme that preserves the original textual RoPE while providing comprehensive frequency spectra and scaled 3D positions for modeling multimodal spatiotemporal data. Moreover, Lumos-1 resorts to a token dependency strategy that obeys intra-frame bidirectionality and inter-frame temporal causality. Based on this dependency strategy, we identify the issue of frame-wise loss imbalance caused by spatial information redundancy and solve it by proposing Autoregressive Discrete Diffusion Forcing (AR-DF). AR-DF introduces temporal tube masking during training with a compatible inference-time masking policy to avoid quality degradation. By using memory-efficient training techniques, we pre-train Lumos-1 on only 48 GPUs, achieving performance comparable to EMU3 on GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V. Code and models are available at https://github.com/alibaba-damo-academy/Lumos.

First-person video assistants are highly anticipated to enhance our daily lives through online video dialogue. However, existing online video assistants often sacrifice assistant efficacy for real-time efficiency by processing low-frame-rate videos with coarse-grained visual features.To overcome the trade-off between efficacy and efficiency, we propose "Fast & Slow Video-Language Thinker" as an onLIne videO assistaNt, LION-FS, achieving real-time, proactive, temporally accurate, and contextually precise responses. LION-FS adopts a two-stage optimization strategy: 1)Fast Path: Routing-Based Response Determination evaluates frame-by-frame whether an immediate response is necessary. To enhance response determination accuracy and handle higher frame-rate inputs efficiently, we employ Token Aggregation Routing to dynamically fuse spatiotemporal features without increasing token numbers, while utilizing Token Dropping Routing to eliminate redundant features. 2)Slow Path: Multi-granularity Keyframe Augmentation optimizes keyframes during response generation. To provide comprehensive and detailed responses beyond atomic actions constrained by training data, fine-grained spatial features and human-environment interaction features are extracted through multi-granular pooling. These features are further integrated into a meticulously designed multimodal Thinking Template to guide more precise response generation. Comprehensive evaluations on online video tasks demonstrate that LION-FS achieves state-of-the-art efficacy and efficiency.

We present Phenaki, a model capable of realistic video synthesis, given a sequence of textual prompts. Generating videos from text is particularly challenging due to the computational cost, limited quantities of high quality text-video data and variable length of videos. To address these issues, we introduce a new model for learning video representation which compresses the video to a small representation of discrete tokens. This tokenizer uses causal attention in time, which allows it to work with variable-length videos. To generate video tokens from text we are using a bidirectional masked transformer conditioned on pre-computed text tokens. The generated video tokens are subsequently de-tokenized to create the actual video. To address data issues, we demonstrate how joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets. Compared to the previous video generation methods, Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts. In addition, compared to the per-frame baselines, the proposed video encoder-decoder computes fewer tokens per video but results in better spatio-temporal consistency.

World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT features a novel compressive tokenization technique that efficiently discretizes high-dimensional visual observations. Leveraging its scalable architecture, we are able to pre-train iVideoGPT on millions of human and robotic manipulation trajectories, establishing a versatile foundation that is adaptable to serve as interactive world models for a wide range of downstream tasks. These include action-conditioned video prediction, visual planning, and model-based reinforcement learning, where iVideoGPT achieves competitive performance compared with state-of-the-art methods. Our work advances the development of interactive general world models, bridging the gap between generative video models and practical model-based reinforcement learning applications.

Text-to-motion generation is a formidable task, aiming to produce human motions that align with the input text while also adhering to human capabilities and physical laws. While there have been advancements in diffusion models, their application in discrete spaces remains underexplored. Current methods often overlook the varying significance of different motions, treating them uniformly. It is essential to recognize that not all motions hold the same relevance to a particular textual description. Some motions, being more salient and informative, should be given precedence during generation. In response, we introduce a Priority-Centric Motion Discrete Diffusion Model (M2DM), which utilizes a Transformer-based VQ-VAE to derive a concise, discrete motion representation, incorporating a global self-attention mechanism and a regularization term to counteract code collapse. We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token within the entire motion sequence. This approach retains the most salient motions during the reverse diffusion process, leading to more semantically rich and varied motions. Additionally, we formulate two strategies to gauge the importance of motion tokens, drawing from both textual and visual indicators. Comprehensive experiments on the HumanML3D and KIT-ML datasets confirm that our model surpasses existing techniques in fidelity and diversity, particularly for intricate textual descriptions.

There has been tremendous progress in multimodal Large Language Models (LLMs). Recent works have extended these models to video input with promising instruction following capabilities. However, an important missing piece is temporal localization. These models cannot accurately answer the "When?" questions. We identify three key aspects that limit their temporal localization capabilities: (i) time representation, (ii) architecture, and (iii) data. We address these shortcomings by proposing Language Instructed Temporal-Localization Assistant (LITA) with the following features: (1) We introduce time tokens that encode timestamps relative to the video length to better represent time in videos. (2) We introduce SlowFast tokens in the architecture to capture temporal information at fine temporal resolution. (3) We emphasize temporal localization data for LITA. In addition to leveraging existing video datasets with timestamps, we propose a new task, Reasoning Temporal Localization (RTL), along with the dataset, ActivityNet-RTL, for learning and evaluating this task. Reasoning temporal localization requires both the reasoning and temporal localization of Video LLMs. LITA demonstrates strong performance on this challenging task, nearly doubling the temporal mean intersection-over-union (mIoU) of baselines. In addition, we show that our emphasis on temporal localization also substantially improves video-based text generation compared to existing Video LLMs, including a 36% relative improvement of Temporal Understanding. Code is available at: https://github.com/NVlabs/LITA

We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three key components: a Segmenter based on SAMURAI for precise object segmentation across frames, a Temporal Analyzer powered by TRACE-Uni for accurate event boundary detection and temporal analysis, and a Captioner using InternVL-2.5 for generating detailed object-centric descriptions. Through spatiotemporal visual prompts and chain-of-thought reasoning, our framework generates detailed, temporally-aware descriptions of objects' attributes, actions, statuses, interactions, and environmental contexts without requiring additional training data. CAT-V supports flexible user interactions through various visual prompts (points, bounding boxes, and irregular regions) and maintains temporal sensitivity by tracking object states and interactions across different time segments. Our approach addresses limitations of existing video captioning methods, which either produce overly abstract descriptions or lack object-level precision, enabling fine-grained, object-specific descriptions while maintaining temporal coherence and spatial accuracy. The GitHub repository for this project is available at https://github.com/yunlong10/CAT-V

Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both traditional techniques and Multimodal Large Language Models (MLLM), most existing methods still rely on coarse temporal understanding and a single visual modality, limiting performance on complex videos. To address this, we introduce Shot-aware Multimodal Audio-enhanced Retrieval of Temporal Segments (SMART), an MLLM-based framework that integrates audio cues and leverages shot-level temporal structure. SMART enriches multimodal representations by combining audio and visual features while applying Shot-aware Token Compression, which selectively retains high-information tokens within each shot to reduce redundancy and preserve fine-grained temporal details. We also refine prompt design to better utilize audio-visual cues. Evaluations on Charades-STA and QVHighlights show that SMART achieves significant improvements over state-of-the-art methods, including a 1.61\% increase in R1@0.5 and 2.59\% gain in R1@0.7 on Charades-STA.

Token-based world models emerged as a promising modular framework, modeling dynamics over token streams while optimizing tokenization separately. While successful in visual environments with discrete actions (e.g., Atari games), their broader applicability remains uncertain. In this paper, we introduce M^{3}, a modular world model that extends this framework, enabling flexible combinations of observation and action modalities through independent modality-specific components. M^{3} integrates several improvements from existing literature to enhance agent performance. Through extensive empirical evaluation across diverse benchmarks, M^{3} achieves state-of-the-art sample efficiency for planning-free world models. Notably, among these methods, it is the first to reach a human-level median score on Atari 100K, with superhuman performance on 13 games. We https://github.com/leor-c/M3{open-source our code and weights}.

Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization, recent methods like TiTok have shown that 1D tokenization can achieve high generation quality by eliminating grid redundancies. However, these methods typically use a fixed number of tokens and thus cannot adapt to an image's inherent complexity. We introduce FlexTok, a tokenizer that projects 2D images into variable-length, ordered 1D token sequences. For example, a 256x256 image can be resampled into anywhere from 1 to 256 discrete tokens, hierarchically and semantically compressing its information. By training a rectified flow model as the decoder and using nested dropout, FlexTok produces plausible reconstructions regardless of the chosen token sequence length. We evaluate our approach in an autoregressive generation setting using a simple GPT-style Transformer. On ImageNet, this approach achieves an FID<2 across 8 to 128 tokens, outperforming TiTok and matching state-of-the-art methods with far fewer tokens. We further extend the model to support to text-conditioned image generation and examine how FlexTok relates to traditional 2D tokenization. A key finding is that FlexTok enables next-token prediction to describe images in a coarse-to-fine "visual vocabulary", and that the number of tokens to generate depends on the complexity of the generation task.

Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by generating coordinates as part of their text output, which requires learning a complicated coordinate system and results in a high token count. Instead, we propose a more intuitive pointing mechanism that directly selects the visual tokens that contain the target concept. Our model generates a special pointing token that cross-attends to the input image or video tokens and selects the appropriate one. To make this model more fine-grained, we follow these pointing tokens with an additional special token that selects a fine-grained subpatch within the initially selected region, and then a third token that specifies a location within that subpatch. We further show that performance improves by generating points sequentially in a consistent order, encoding the relative position of the previously selected point, and including a special no-more-points class when selecting visual tokens. Using this method, we set a new state-of-the-art on image pointing (70.7% on PointBench), set a new state-of-the-art among fully open models on GUI pointing (61.1% on ScreenSpotPro), and improve video pointing (59.1% human preference win rate vs. a text coordinate baseline) and tracking (+6.3% gain on Molmo2Track). We additionally show that our method achieves much higher sample efficiency and discuss the qualitative differences that emerge from this design change.

Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and over 99% of robotics/gameplay clips contain overlapping events, yet existing multi-event generators rest on a single-active-prompt assumption. However, modern video generators, such as Diffusion Transformers (DiT), represent time as discrete points through point-wise positional encodings. This formulation creates a fundamental dimension mismatch: temporally extended intervals and overlapping events are mathematically unrepresentable to the attention mechanism. In this paper, we propose Time Interval Encoding (TIE), a principled, plug-and-play interval-aware generalization of rotary embeddings that elevates time intervals to first-class primitives inside DiT cross-attention. Rather than introducing another heuristic interval embedding, we show that, within RoPE-compatible bilinear attention, TIE is characterized by two basic principles: Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration. Empirically, TIE preserves the visual quality of the base DiT model while substantially improving temporal controllability. In our experiments on the OmniEvents dataset, it improves human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03% and reduces temporal boundary error from 0.261s to 0.073s, while also improving trajectory-level temporal alignment metrics. The code and dataset are available at https://github.com/MatrixTeam-AI/TIE.

Despite rapid progress in video generation, existing models are incapable of producing vector animation, a dominant and highly expressive form of multimedia on the Internet. Vector animations offer resolution-independence, compactness, semantic structure, and editable parametric motion representations, yet current generative models operate exclusively in raster space and thus cannot synthesize them. Meanwhile, recent advances in large multimodal models demonstrate strong capabilities in generating structured data such as slides, 3D meshes, LEGO sequences, and indoor layouts, suggesting that native vector animation generation may be achievable. In this work, we present the first framework for tokenizing and autoregressively generating vector animations. We adopt Lottie, a widely deployed JSON-based animation standard, and design a tailored Lottie Tokenizer that encodes layered geometric primitives, transforms, and keyframe-based motion into a compact and semantically aligned token sequence. To support large-scale training, we also construct LottieAnimation-660K, the largest and most diverse vector animation dataset to date, consisting of 660k real-world Lottie animation and 15M static Lottie image files curated from broad Internet sources. Building upon these components, we finetune Qwen-VL to create LottieGPT, a native multimodal model capable of generating coherent, editable vector animations directly from natural language or visual prompts. Experiments show that our tokenizer dramatically reduces sequence length while preserving structural fidelity, enabling effective autoregressive learning of dynamic vector content. LottieGPT exhibits strong generalization across diverse animation styles and outperforms previous state-of-the-art models on SVG generation (a special case of single-frame vector animation).

We introduce InteractiveVideo, a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction, allowing users to instruct the generative model through various intuitive mechanisms during the whole generation process, e.g. text and image prompts, painting, drag-and-drop, etc. We propose a Synergistic Multimodal Instruction mechanism, designed to seamlessly integrate users' multimodal instructions into generative models, thus facilitating a cooperative and responsive interaction between user inputs and the generative process. This approach enables iterative and fine-grained refinement of the generation result through precise and effective user instructions. With InteractiveVideo, users are given the flexibility to meticulously tailor key aspects of a video. They can paint the reference image, edit semantics, and adjust video motions until their requirements are fully met. Code, models, and demo are available at https://github.com/invictus717/InteractiveVideo

Cross-view geo-localization matches ground-level observations against geo-tagged satellite imagery. Recent methods show that sequential queries such as video clips yield richer spatiotemporal cues than single images, yet they overlook a complementary sequential modality: route descriptions -- which capture the same trajectory at a higher level of abstraction and are often the only input available (e.g., a user directing an autonomous vehicle to a pickup point). To bridge this gap, we introduce SeqGeo-VL, a dataset of sim39K video-text-satellite triplets, and TrajLoc, a unified framework capable of processing both video clips and route descriptions. By leveraging both dense visual and abstract linguistic semantics, TrajLoc enables these modalities to mutually reinforce cross-view matching. We further propose TrajMod, a lightweight module that conditions query embeddings on trajectory geometry, yielding spatially-aware representations. Experiments show that TrajLoc achieves substantial gains over state-of-the-art methods on both video and text geo-localization. The project page is available at https://humblegamer.github.io/trajloc/.

First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of Transformer-based Video-LLMs makes dense visual tokens computationally expensive. Existing token pruning paradigms predominantly rely on discrete static snapshots, failing to preserve the motion and geometric cues essential for reasoning. We propose Event Cascade Pruning (ECP), to our knowledge the first training-free framework that leverages the high-frequency motion cues from event cameras as a continuous event-guided motion prior to guide token selection. ECP combines three stages: Event-Triggered Causal Sampling to anchor motion-informative keyframes, Event-guided Motion Saliency Filtering to suppress event-inactive visual tokens, and Event-Attention Ranking Fusion to calibrate spatial attention with motion-salient dynamics. With 80% visual token reduction, ECP outperforms the full-token baseline (37.62% vs. 36.31%) while achieving 1.89x inference speedup and 52% GFLOPs reduction. We further introduce ESR-Real, the first real-world RGB-event benchmark for first-person spatial reasoning, where ECP improves accuracy by 2.68 percentage points over full-token baselines.

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion (e.g., even lacking the ability to be prompted for objects moving from left to right). To address these limitations, we introduce LLM-grounded Video Diffusion (LVD). Instead of directly generating videos from the text inputs, LVD first leverages a large language model (LLM) to generate dynamic scene layouts based on the text inputs and subsequently uses the generated layouts to guide a diffusion model for video generation. We show that LLMs are able to understand complex spatiotemporal dynamics from text alone and generate layouts that align closely with both the prompts and the object motion patterns typically observed in the real world. We then propose to guide video diffusion models with these layouts by adjusting the attention maps. Our approach is training-free and can be integrated into any video diffusion model that admits classifier guidance. Our results demonstrate that LVD significantly outperforms its base video diffusion model and several strong baseline methods in faithfully generating videos with the desired attributes and motion patterns.

Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scenes efficiently by dynamically scanning and focusing on salient regions in a sequential "blink-like" process. Motivated by this strategy, we first investigate whether MLLMs exhibit similar behavior. Our pilot analysis reveals that MLLMs naturally attend to different visual regions across layers and that selectively allocating more computation to salient tokens can enhance visual perception. Building on this insight, we propose Blink, a dynamic visual token resolution framework that emulates the human-inspired process within a single forward pass. Specifically, Blink includes two modules: saliency-guided scanning and dynamic token resolution. It first estimates the saliency of visual tokens in each layer based on the attention map, and extends important tokens through a plug-and-play token super-resolution (TokenSR) module. In the next layer, it drops the extended tokens when they lose focus. This dynamic mechanism balances broad exploration and fine-grained focus, thereby enhancing visual perception adaptively and efficiently. Extensive experiments validate Blink, demonstrating its effectiveness in enhancing visual perception and multimodal understanding.

We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation, or video-generation modules, Wan-Streamer does not rely on external language, speech, avatar, or video-generation modules: perception, reasoning, generation, response timing, turn management, and cross-modal synchronization are learned jointly within one unified model, reducing pipeline latency and error accumulation. To support natural audio-visual responsiveness, we redesign the entire stack around streamability, including causal encoders, causal decoders, block-causal attention, and low-latency multimodal token scheduling, enabling streaming units as short as 160 ms at 25 fps. Wan-Streamer achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency when combined with 350 ms bidirectional network latency, supporting sub-second duplex audio-visual communication. These results position Wan-Streamer as a unified, end-to-end, multimodal interactive foundation model for low-latency streaming interaction.

Video diffusion models have achieved remarkable progress in generating high-quality videos. However, these models struggle to represent the temporal succession of multiple events in real-world videos and lack explicit mechanisms to control when semantic concepts appear, how long they persist, and the order in which multiple events occur. Such control is especially important for movie-grade video synthesis, where coherent storytelling depends on precise timing, duration, and transitions between events. When using a single paragraph-style prompt to describe a sequence of complex events, models often exhibit semantic entanglement, where concepts intended for different moments in the video bleed into one another, resulting in poor text-video alignment. To address these limitations, we propose Prompt Relay, an inference-time, plug-and-play method to enable fine-grained temporal control in multi-event video generation, requiring no architectural modifications and no additional computational overhead. Prompt Relay introduces a penalty into the cross-attention mechanism, so that each temporal segment attends only to its assigned prompt, allowing the model to represent one semantic concept at a time and thereby improving temporal prompt alignment, reducing semantic interference, and enhancing visual quality.

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the computational cost of the diffusion model to scale linearly with the frame rate. The paper proposes the Duration-Proportional Information Assumption: the upper bound on the information capacity of a video is proportional to the duration rather than the number of frames. Based on this insight, the paper introduces VFRTok, a Transformer-based video tokenizer, that enables variable frame rate encoding and decoding through asymmetric frame rate training between the encoder and decoder. Furthermore, the paper proposes Partial Rotary Position Embeddings (RoPE) to decouple position and content modeling, which groups correlated patches into unified tokens. The Partial RoPE effectively improves content-awareness, enhancing the video generation capability. Benefiting from the compact and continuous spatio-temporal representation, VFRTok achieves competitive reconstruction quality and state-of-the-art generation fidelity while using only 1/8 tokens compared to existing tokenizers.

The Transformer architecture is shown to provide a powerful machine transduction framework for online handwritten gestures corresponding to glyph strokes of natural language sentences. The attention mechanism is successfully used to create latent representations of an end-to-end encoder-decoder model, solving multi-level segmentation while also learning some language features and syntax rules. The additional use of a large decoding space with some learned Byte-Pair-Encoding (BPE) is shown to provide robustness to ablated inputs and syntax rules. The encoder stack was directly fed with spatio-temporal data tokens potentially forming an infinitely large input vocabulary, an approach that finds applications beyond that of this work. Encoder transfer learning capabilities is also demonstrated on several languages resulting in faster optimisation and shared parameters. A new supervised dataset of online handwriting gestures suitable for generic handwriting recognition tasks was used to successfully train a small transformer model to an average normalised Levenshtein accuracy of 96% on English or German sentences and 94% in French.

Large Language Models (LLMs) have demonstrated remarkable generalization across diverse tasks, leading individuals to increasingly use them as personal assistants and universal computing engines. Nevertheless, a notable obstacle emerges when feeding numerical/temporal data into these models, such as data sourced from wearables or electronic health records. LLMs employ tokenizers in their input that break down text into smaller units. However, tokenizers are not designed to represent numerical values and might struggle to understand repetitive patterns and context, treating consecutive values as separate tokens and disregarding their temporal relationships. Here, we discuss recent works that employ LLMs for human-centric tasks such as in mobile health sensing and present a case study showing that popular LLMs tokenize temporal data incorrectly. To address that, we highlight potential solutions such as prompt tuning with lightweight embedding layers as well as multimodal adapters, that can help bridge this "modality gap". While the capability of language models to generalize to other modalities with minimal or no finetuning is exciting, this paper underscores the fact that their outputs cannot be meaningful if they stumble over input nuances.

Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying viewpoints. Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement. However, camera movement may introduce new objects to the scene or eliminate existing ones, thereby overlaying and affecting the preceding narrative. Especially in videos with numerous camera movements, the interplay between multiple plots becomes increasingly complex. This paper introduces and examines integral spatio-temporal consistency, considering the synergy between plot progression and camera techniques, and the long-term impact of prior content on subsequent generation. Our research encompasses dataset construction through to the development of the model. Initially, we constructed a DropletVideo-10M dataset, which comprises 10 million videos featuring dynamic camera motion and object actions. Each video is annotated with an average caption of 206 words, detailing various camera movements and plot developments. Following this, we developed and trained the DropletVideo model, which excels in preserving spatio-temporal coherence during video generation. The DropletVideo dataset and model are accessible at https://dropletx.github.io.

We present WorldCanvas, a framework for promptable world events that enables rich, user-directed simulation by combining text, trajectories, and reference images. Unlike text-only approaches and existing trajectory-controlled image-to-video methods, our multimodal approach combines trajectories -- encoding motion, timing, and visibility -- with natural language for semantic intent and reference images for visual grounding of object identity, enabling the generation of coherent, controllable events that include multi-agent interactions, object entry/exit, reference-guided appearance and counterintuitive events. The resulting videos demonstrate not only temporal coherence but also emergent consistency, preserving object identity and scene despite temporary disappearance. By supporting expressive world events generation, WorldCanvas advances world models from passive predictors to interactive, user-shaped simulators. Our project page is available at: https://worldcanvas.github.io/.

Current dialogue systems focus more on textual and speech context knowledge and are usually based on two speakers. Some recent work has investigated static image-based dialogue. However, several real-world human interactions also involve dynamic visual context (similar to videos) as well as dialogue exchanges among multiple speakers. To move closer towards such multimodal conversational skills and visually-situated applications, we introduce a new video-context, many-speaker dialogue dataset based on live-broadcast soccer game videos and chats from Twitch.tv. This challenging testbed allows us to develop visually-grounded dialogue models that should generate relevant temporal and spatial event language from the live video, while also being relevant to the chat history. For strong baselines, we also present several discriminative and generative models, e.g., based on tridirectional attention flow (TriDAF). We evaluate these models via retrieval ranking-recall, automatic phrase-matching metrics, as well as human evaluation studies. We also present dataset analyses, model ablations, and visualizations to understand the contribution of different modalities and model components.

Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and controllability beyond text prompts. To tackle these challenges, we propose MultiShotMaster, a framework for highly controllable multi-shot video generation. We extend a pretrained single-shot model by integrating two novel variants of RoPE. First, we introduce Multi-Shot Narrative RoPE, which applies explicit phase shift at shot transitions, enabling flexible shot arrangement while preserving the temporal narrative order. Second, we design Spatiotemporal Position-Aware RoPE to incorporate reference tokens and grounding signals, enabling spatiotemporal-grounded reference injection. In addition, to overcome data scarcity, we establish an automated data annotation pipeline to extract multi-shot videos, captions, cross-shot grounding signals and reference images. Our framework leverages the intrinsic architectural properties to support multi-shot video generation, featuring text-driven inter-shot consistency, customized subject with motion control, and background-driven customized scene. Both shot count and duration are flexibly configurable. Extensive experiments demonstrate the superior performance and outstanding controllability of our framework.

Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Temporal-ConvNet) are unclear. In this work, we first demonstrate a strong baseline two-stream ConvNet using ResNet-101. We use this baseline to thoroughly examine the use of both RNNs and Temporal-ConvNets for extracting spatiotemporal information. Building upon our experimental results, we then propose and investigate two different networks to further integrate spatiotemporal information: 1) temporal segment RNN and 2) Inception-style Temporal-ConvNet. We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance. However, each of these methods require proper care to achieve state-of-the-art performance; for example, LSTMs require pre-segmented data or else they cannot fully exploit temporal information. Our analysis identifies specific limitations for each method that could form the basis of future work. Our experimental results on UCF101 and HMDB51 datasets achieve state-of-the-art performances, 94.1% and 69.0%, respectively, without requiring extensive temporal augmentation.

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.

Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches predominantly train models to associate events with timestamps in the forward video only. This paradigm hinders VLMs from capturing the inherent temporal structure and directionality of events, thereby limiting robustness and generalization. To address this limitation, inspired by the arrow of time in physics, which characterizes the intrinsic directionality of temporal processes, we propose ArrowGEV, a reinforcement learning framework that explicitly models temporal directionality in events to improve both event grounding and temporal directionality understanding in VLMs. Specifically, we categorize events into time-sensitive (e.g., putting down a bag) and time-insensitive (e.g., holding a towel in the left hand). The former denote events whose reversal substantially alters their meaning, while the latter remain semantically unchanged under reversal. For time-sensitive events, ArrowGEV introduces a reward that encourages VLMs to discriminate between forward and backward videos, whereas for time-insensitive events, it enforces consistent grounding across both directions. Extensive experiments demonstrate that ArrowGEV not only improves grounding precision and temporal directionality recognition, but also enhances general video understanding and reasoning ability.

Recent approaches have demonstrated the promise of using diffusion models to generate interactive and explorable worlds. However, most of these methods face critical challenges such as excessively large parameter sizes, reliance on lengthy inference steps, and rapidly growing historical context, which severely limit real-time performance and lack text-controlled generation capabilities. To address these challenges, we propose \method, a novel framework designed to generate realistic, interactive, and continuous worlds from a single image or text prompt. \method achieves this through a carefully designed framework that supports keyboard-based exploration of the generated worlds. The framework comprises three core components: (1) a long-video generation framework integrating unified context compression with linear attention; (2) a real-time streaming acceleration strategy powered by bidirectional attention distillation and an enhanced text embedding scheme; (3) a text-controlled method for generating world events. We have provided the codebase in the supplementary material.

Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts. Our code and models are publicly available at https://mathis.petrovich.fr/stmc.

Active Real-time interaction with video LLMs introduces a new paradigm for human-computer interaction, where the model not only understands user intent but also responds while continuously processing streaming video on the fly. Unlike offline video LLMs, which analyze the entire video before answering questions, active real-time interaction requires three capabilities: 1) Perception: real-time video monitoring and interaction capturing. 2) Decision: raising proactive interaction in proper situations, 3) Reaction: continuous interaction with users. However, inherent conflicts exist among the desired capabilities. The Decision and Reaction require a contrary Perception scale and grain, and the autoregressive decoding blocks the real-time Perception and Decision during the Reaction. To unify the conflicted capabilities within a harmonious system, we present Dispider, a system that disentangles Perception, Decision, and Reaction. Dispider features a lightweight proactive streaming video processing module that tracks the video stream and identifies optimal moments for interaction. Once the interaction is triggered, an asynchronous interaction module provides detailed responses, while the processing module continues to monitor the video in the meantime. Our disentangled and asynchronous design ensures timely, contextually accurate, and computationally efficient responses, making Dispider ideal for active real-time interaction for long-duration video streams. Experiments show that Dispider not only maintains strong performance in conventional video QA tasks, but also significantly surpasses previous online models in streaming scenario responses, thereby validating the effectiveness of our architecture. The code and model are released at https://github.com/Mark12Ding/Dispider.

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently disrupt spatial layouts and temporal continuity by disregarding positional relationships. In this work, we propose a novel encoding operator dubbed as Positional Preservation Embedding (PPE), which has the main hallmark of preservation of spatiotemporal structure during visual token compression. PPE explicitly introduces the disentangled encoding of 3D positions in the token dimension, enabling each compressed token to encapsulate different positions from multiple original tokens. Furthermore, we show that PPE can effectively support cascade clustering -- a progressive token compression strategy that leads to better performance retention. PPE is a parameter-free and generic operator that can be seamlessly integrated into existing token merging methods without any adjustments. Applied to state-of-the-art token merging framework, PPE achieves consistent improvements of 2%sim5% across multiple vision-language benchmarks, including MMBench (general vision understanding), TextVQA (layout understanding) and VideoMME (temporal understanding). These results demonstrate that preserving positional cues is critical for efficient and effective MLLM reasoning.

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where too few tokens will result in overly lossy encodings, and too many tokens will result in prohibitively long sequence lengths. In this work, we introduce ElasticTok, a method that conditions on prior frames to adaptively encode a frame into a variable number of tokens. To enable this in a computationally scalable way, we propose a masking technique that drops a random number of tokens at the end of each frames's token encoding. During inference, ElasticTok can dynamically allocate tokens when needed -- more complex data can leverage more tokens, while simpler data only needs a few tokens. Our empirical evaluations on images and video demonstrate the effectiveness of our approach in efficient token usage, paving the way for future development of more powerful multimodal models, world models, and agents.

Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis toward dynamic, interactive simulation. However, current approaches remain limited by rigid action schemas and high annotation costs, restricting their ability to model diverse in-game interactions and player-driven dynamics. To address these challenges, we introduce Hunyuan-GameCraft-2, a new paradigm of instruction-driven interaction for generative game world modeling. Instead of relying on fixed keyboard inputs, our model allows users to control game video contents through natural language prompts, keyboard, or mouse signals, enabling flexible and semantically rich interaction within generated worlds. We formally defined the concept of interactive video data and developed an automated process to transform large-scale, unstructured text-video pairs into causally aligned interactive datasets. Built upon a 14B image-to-video Mixture-of-Experts(MoE) foundation model, our model incorporates a text-driven interaction injection mechanism for fine-grained control over camera motion, character behavior, and environment dynamics. We introduce an interaction-focused benchmark, InterBench, to evaluate interaction performance comprehensively. Extensive experiments demonstrate that our model generates temporally coherent and causally grounded interactive game videos that faithfully respond to diverse and free-form user instructions such as "open the door", "draw a torch", or "trigger an explosion".

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a unified vision-language model capable of comprehending and engaging in conversations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to efficiently utilize a limited number of visual tokens to simultaneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level semantic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Extensive experimental results demonstrate that Chat-UniVi, as a unified model, consistently outperforms even existing methods exclusively designed for either images or videos.

Video captioning aims to convey dynamic scenes from videos using natural language, facilitating the understanding of spatiotemporal information within our environment. Although there have been recent advances, generating detailed and enriched video descriptions continues to be a substantial challenge. In this work, we introduce Video ChatCaptioner, an innovative approach for creating more comprehensive spatiotemporal video descriptions. Our method employs a ChatGPT model as a controller, specifically designed to select frames for posing video content-driven questions. Subsequently, a robust algorithm is utilized to answer these visual queries. This question-answer framework effectively uncovers intricate video details and shows promise as a method for enhancing video content. Following multiple conversational rounds, ChatGPT can summarize enriched video content based on previous conversations. We qualitatively demonstrate that our Video ChatCaptioner can generate captions containing more visual details about the videos. The code is publicly available at https://github.com/Vision-CAIR/ChatCaptioner

Next-generation AI companions must go beyond general video understanding to resolve spatial and temporal references in dynamic, real-world environments. Existing Video Large Language Models (Video LLMs), while capable of coarse-level comprehension, struggle with fine-grained, spatiotemporal reasoning, especially when user queries rely on time-based event references for temporal anchoring, or gestural cues for spatial anchoring to clarify object references and positions. To bridge this critical gap, we introduce Strefer, a synthetic instruction data generation framework designed to equip Video LLMs with spatiotemporal referring and reasoning capabilities. Strefer produces diverse instruction-tuning data using a data engine that pseudo-annotates temporally dense, fine-grained video metadata, capturing rich spatial and temporal information in a structured manner, including subjects, objects, their locations as masklets, and their action descriptions and timelines. Our approach enhances the ability of Video LLMs to interpret spatial and temporal references, fostering more versatile, space-time-aware reasoning essential for real-world AI companions. Without using proprietary models, costly human annotation, or the need to annotate large volumes of new videos, experimental evaluations show that models trained with data produced by Strefer outperform baselines on tasks requiring spatial and temporal disambiguation. Additionally, these models exhibit enhanced space-time-aware reasoning, establishing a new foundation for perceptually grounded, instruction-tuned Video LLMs.

Recent advances in interactive video generations have demonstrated diffusion model's potential as world models by capturing complex physical dynamics and interactive behaviors. However, existing interactive world models depend on bidirectional attention and lengthy inference steps, severely limiting real-time performance. Consequently, they are hard to simulate real-world dynamics, where outcomes must update instantaneously based on historical context and current actions. To address this, we present Matrix-Game 2.0, an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion. Our framework consists of three key components: (1) A scalable data production pipeline for Unreal Engine and GTA5 environments to effectively produce massive amounts (about 1200 hours) of video data with diverse interaction annotations; (2) An action injection module that enables frame-level mouse and keyboard inputs as interactive conditions; (3) A few-step distillation based on the casual architecture for real-time and streaming video generation. Matrix Game 2.0 can generate high-quality minute-level videos across diverse scenes at an ultra-fast speed of 25 FPS. We open-source our model weights and codebase to advance research in interactive world modeling.

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-k context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing

Large language models (LLMs) have the potential to impact a wide range of creative domains, but the application of LLMs to animation is underexplored and presents novel challenges such as how users might effectively describe motion in natural language. In this paper, we present Keyframer, a design tool for animating static images (SVGs) with natural language. Informed by interviews with professional animation designers and engineers, Keyframer supports exploration and refinement of animations through the combination of prompting and direct editing of generated output. The system also enables users to request design variants, supporting comparison and ideation. Through a user study with 13 participants, we contribute a characterization of user prompting strategies, including a taxonomy of semantic prompt types for describing motion and a 'decomposed' prompting style where users continually adapt their goals in response to generated output.We share how direct editing along with prompting enables iteration beyond one-shot prompting interfaces common in generative tools today. Through this work, we propose how LLMs might empower a range of audiences to engage with animation creation.

This paper focuses on enhancing human-agent communication by integrating spatial context into virtual agents' non-verbal behaviors, specifically gestures. Recent advances in co-speech gesture generation have primarily utilized data-driven methods, which create natural motion but limit the scope of gestures to those performed in a void. Our work aims to extend these methods by enabling generative models to incorporate scene information into speech-driven gesture synthesis. We introduce a novel synthetic gesture dataset tailored for this purpose. This development represents a critical step toward creating embodied conversational agents that interact more naturally with their environment and users.

Reasoning goes beyond language; the real world requires reasoning about space, time, affordances, and much more that words alone cannot convey. Existing multimodal models exploring the potential of reasoning with images are brittle and do not scale. They rely on calling specialist tools, costly generation of images, or handcrafted reasoning data to switch between text and image thoughts. Instead, we offer a simpler alternative -- Mull-Tokens -- modality-agnostic latent tokens pre-trained to hold intermediate information in either image or text modalities to let the model think free-form towards the correct answer. We investigate best practices to train Mull-Tokens inspired by latent reasoning frameworks. We first train Mull-Tokens using supervision from interleaved text-image traces, and then fine-tune without any supervision by only using the final answers. Across four challenging spatial reasoning benchmarks involving tasks such as solving puzzles and taking different perspectives, we demonstrate that Mull-Tokens improve upon several baselines utilizing text-only reasoning or interleaved image-text reasoning, achieving a +3% average improvement and up to +16% on a puzzle solving reasoning-heavy split compared to our strongest baseline. Adding to conversations around challenges in grounding textual and visual reasoning, Mull-Tokens offers a simple solution to abstractly think in multiple modalities.

Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone. Diffusion Transformers (DiTs) can natively ingest heterogeneous tokens stemming from texts and images, but they lack mechanisms for determining where and how these tokens should influence the output. We introduce appearance pointers, compact tokens that guide DiTs toward the correct appearance cues at the correct spatial locations by aligning text or image inputs with user-specified masks. Appearance pointers are produced by a region correspondence network and refined through a spatial aggregation mechanism, enabling the model to handle multiple regional descriptions without significantly increasing token load. Our approach introduces the first modality-agnostic interface for localized multimodal control in a DiT without retraining the base model from scratch. Across a range of metrics, our single model reaches or surpasses the performance of modality-specific state of the art methods, offering a simple and extensible path toward precise, region-aware, multimodal guidance in generative image synthesis.

Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and mis-alignments with user instructions, especially in scenarios involving complex scene understanding, human-object interactions, multi-stage actions, and in-context motion reasoning. To address these challenges, we propose Plan-X, a framework that explicitly enforces high-level semantic planning to instruct video generation process. At its core lies a Semantic Planner, a learnable multimodal language model that reasons over the user's intent from both text prompts and visual context, and autoregressively generates a sequence of text-grounded spatio-temporal semantic tokens. These semantic tokens, complementary to high-level text prompt guidance, serve as structured "semantic sketches" over time for the video diffusion model, which has its strength at synthesizing high-fidelity visual details. Plan-X effectively integrates the strength of language models in multimodal in-context reasoning and planning, together with the strength of diffusion models in photorealistic video synthesis. Extensive experiments demonstrate that our framework substantially reduces visual hallucinations and enables fine-grained, instruction-aligned video generation consistent with multimodal context.

Current open-source diffusion models struggle to generate stable and synchronized audio-visual content, particularly in scenarios demanding complex semantic reasoning. The root cause is that existing methods rely on coarse text embeddings from off-the-shelf encoders to guide audio-video denoising, which discards fine-grained semantics and, critically, lacks a shared long-horizon plan, leading to uncoordinated denoising trajectories and fragile cross-modal alignment. We propose Baton, the first framework that introduces explicit semantic planning into joint video-audio generation. Our key insight is that complementing coarse text guidance with semantically rich, modality-aware planned tokens, jointly reasoned and mutually aligned before denoising, can simultaneously restore fine-grained semantic detail and establish a shared blueprint that coordinates both audio and video denoising trajectories. Concretely, Baton first introduces the VA-Planner, a multimodal language model equipped with dual semantic alignment towers, where learnable queries cross-attend to both video and audio features to produce a pair of semantically aligned video and audio planned tokens as keyframe-level blueprints. These planned tokens are injected into the diffusion backbone via cross-attention layers, providing temporally grounded guidance complementary to coarse text embeddings. Since planned tokens do not share one-to-one spatial-temporal correspondence with diffusion latents, we further propose Relative Semantic RoPE, a relative positional encoding that maps planned tokens and latents into a shared spatial-temporal coordinate frame, enabling each latent to accurately attend to its positionally corresponding semantic cues. Experiments on benchmarks show the effectiveness of Baton both qualitatively and quantitatively.

Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for explicit multi-shot cinematic video generation built upon a video diffusion foundation model. Our method introduces learnable planning tokens that capture shot-level transition cues and can be seamlessly integrated with the original video generation tokens to control transition timestamps. Unlike standard video generation tokens, the proposed planning tokens are equipped with Fractional Temporal Rotary Position Embedding (FRoPE), enabling shot transitions to be modeled at the frame level. Experiments demonstrate that ShotPlan significantly outperforms existing cinematic video generation methods, offering more flexible shot management and stronger inter-shot consistency.

Large language and multimodal models (LLMs and LMMs) exhibit strong inference capabilities but are often limited by slow decoding speeds. This challenge is especially acute in LMMs, where visual inputs typically comprise more tokens with lower information density than text -- an issue exacerbated by recent trends toward finer-grained visual tokenizations to boost performance. Speculative decoding has been effective in accelerating LLM inference by using a smaller draft model to generate candidate tokens, which are then selectively verified by the target model, improving speed without sacrificing output quality. While this strategy has been extended to LMMs, existing methods largely overlook the unique properties of visual inputs and depend solely on text-based draft models. In this work, we propose FLASH (Fast Latent-Aware Semi-Autoregressive Heuristics), a speculative decoding framework designed specifically for LMMs, which leverages two key properties of multimodal data to design the draft model. First, to address redundancy in visual tokens, we propose a lightweight latent-aware token compression mechanism. Second, recognizing that visual objects often co-occur within a scene, we employ a semi-autoregressive decoding strategy to generate multiple tokens per forward pass. These innovations accelerate draft decoding while maintaining high acceptance rates, resulting in faster overall inference. Experiments show that FLASH significantly outperforms prior speculative decoding approaches in both unimodal and multimodal settings, achieving up to 2.68times speed-up on video captioning and 2.55times on visual instruction tuning tasks compared to the original LMM. Our code is available https://github.com/ZihuaEvan/FlashSD/{[here]}.

Integrating CNNs and RNNs to capture spatiotemporal dependencies is a prevalent strategy for spatiotemporal prediction tasks. However, the property of CNNs to learn local spatial information decreases their efficiency in capturing spatiotemporal dependencies, thereby limiting their prediction accuracy. In this paper, we propose a new recurrent cell, SwinLSTM, which integrates Swin Transformer blocks and the simplified LSTM, an extension that replaces the convolutional structure in ConvLSTM with the self-attention mechanism. Furthermore, we construct a network with SwinLSTM cell as the core for spatiotemporal prediction. Without using unique tricks, SwinLSTM outperforms state-of-the-art methods on Moving MNIST, Human3.6m, TaxiBJ, and KTH datasets. In particular, it exhibits a significant improvement in prediction accuracy compared to ConvLSTM. Our competitive experimental results demonstrate that learning global spatial dependencies is more advantageous for models to capture spatiotemporal dependencies. We hope that SwinLSTM can serve as a solid baseline to promote the advancement of spatiotemporal prediction accuracy. The codes are publicly available at https://github.com/SongTang-x/SwinLSTM.

Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large language models, where the quantization errors can limit semantic expressiveness and degrade the capability of vision-language understanding. To address this, we introduce MingTok, a new family of visual tokenizers with a continuous latent space, for unified autoregressive generation and understanding. While understanding tasks favor discriminative high-dimensional features, generation tasks prefer compact low-level codes. Thus, to reconcile these competing demands, MingTok adopts a three-stage sequential architecture involving low-level encoding, semantic expansion, and visual reconstruction. Built on top of it, Ming-UniVision eliminates the need for task-specific visual representations, and unifies diverse vision-language tasks under a single autoregrsssive prediction paradigm. By formulating both understanding and generation as next-token prediction in a shared continuous space, it seamlessly supports multi-round, in-context tasks such as iterative understanding, generation and editing. Empirically, we find that using a unified continuous visual representation reconciles the competing requirements on the tokenizers by the understanding and generation tasks, thereby leading to state-of-the-art level performance across both domains. We hope our findings will facilitate unified visual tokenization in the continuous domain. Inference code and model weights are released to benefit community.

Effective and efficient tokenization plays an important role in image representation and generation. Conventional methods, constrained by uniform 2D/1D grid tokenization, are inflexible to represent regions with varying shapes and textures and at different locations, limiting their efficacy of feature representation. In this work, we propose GPSToken, a novel Gaussian Parameterized Spatially-adaptive Tokenization framework, to achieve non-uniform image tokenization by leveraging parametric 2D Gaussians to dynamically model the shape, position, and textures of different image regions. We first employ an entropy-driven algorithm to partition the image into texture-homogeneous regions of variable sizes. Then, we parameterize each region as a 2D Gaussian (mean for position, covariance for shape) coupled with texture features. A specialized transformer is trained to optimize the Gaussian parameters, enabling continuous adaptation of position/shape and content-aware feature extraction. During decoding, Gaussian parameterized tokens are reconstructed into 2D feature maps through a differentiable splatting-based renderer, bridging our adaptive tokenization with standard decoders for end-to-end training. GPSToken disentangles spatial layout (Gaussian parameters) from texture features to enable efficient two-stage generation: structural layout synthesis using lightweight networks, followed by structure-conditioned texture generation. Experiments demonstrate the state-of-the-art performance of GPSToken, which achieves rFID and FID scores of 0.65 and 1.50 on image reconstruction and generation tasks using 128 tokens, respectively. Codes and models of GPSToken can be found at https://github.com/xtudbxk/GPSToken{https://github.com/xtudbxk/GPSToken}.

Graph Neural Networks have gained huge interest in the past few years. These powerful algorithms expanded deep learning models to non-Euclidean space and were able to achieve state of art performance in various applications including recommender systems and social networks. However, this performance is based on static graph structures assumption which limits the Graph Neural Networks performance when the data varies with time. Spatiotemporal Graph Neural Networks are extension of Graph Neural Networks that takes the time factor into account. Recently, various Spatiotemporal Graph Neural Network algorithms were proposed and achieved superior performance compared to other deep learning algorithms in several time dependent applications. This survey discusses interesting topics related to Spatiotemporal Graph Neural Networks, including algorithms, applications, and open challenges.

Video Large Language Models (VLMs) have achieved remarkable results on a variety of vision language tasks, yet their practical use is limited by the "needle in a haystack" problem: the massive number of visual tokens produced from raw video frames exhausts the model's context window. Existing solutions alleviate this issue by selecting a sparse set of frames, thereby reducing token count, but such frame-wise selection discards essential temporal dynamics, leading to suboptimal reasoning about motion and event continuity. In this work we systematically explore the impact of temporal information and demonstrate that extending selection from isolated key frames to key clips, which are short, temporally coherent segments, improves video understanding. To maintain a fixed computational budget while accommodating the larger token footprint of clips, we propose an adaptive resolution strategy that dynamically balances spatial resolution and clip length, ensuring a constant token count per video. Experiments on three long-form video benchmarks demonstrate that our training-free approach, F2C, outperforms uniform sampling up to 8.1%, 5.6%, and 10.3% on Video-MME, LongVideoBench and MLVU benchmarks, respectively. These results highlight the importance of preserving temporal coherence in frame selection and provide a practical pathway for scaling Video LLMs to real world video understanding applications. Project webpage is available at https://guangyusun.com/f2c .

Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with shallow-layer overhead, yielding suboptimal spatiotemporal reduction and underutilizing long-context compressibility. All of them often discard subtle yet informative context from merged or pruned tokens. In this paper, we propose a new perspective that elaborates token Anchors within intra-frame and inter-frame to comprehensively aggregate the informative contexts via local-global Optimal Transport (AOT). Specifically, we first establish local- and global-aware token anchors within each frame under the attention guidance, which then optimal transport aggregates the informative contexts from pruned tokens, constructing intra-frame token anchors. Then, building on the temporal frame clips, the first frame within each clip will be considered as the keyframe anchors to ensemble similar information from consecutive frames through optimal transport, while keeping distinct tokens to represent temporal dynamics, leading to efficient token reduction in a training-free manner. Extensive evaluations show that our proposed AOT obtains competitive performances across various short- and long-video benchmarks on leading video LLMs, obtaining substantial computational efficiency while preserving temporal and visual fidelity. Project webpage: https://tyroneli.github.io/AOT{AOT}.

While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide a user-friendly interface for visual prompting. To address this challenge, we introduce a novel multimodal model capable of decoding arbitrary visual prompts. This allows users to intuitively mark images and interact with the model using natural cues like a "red bounding box" or "pointed arrow". Our simple design directly overlays visual markers onto the RGB image, eliminating the need for complex region encodings, yet achieves state-of-the-art performance on region-understanding tasks like Visual7W, PointQA, and Visual Commonsense Reasoning benchmark. Furthermore, we present ViP-Bench, a comprehensive benchmark to assess the capability of models in understanding visual prompts across multiple dimensions, enabling future research in this domain. Code, data, and model are publicly available.

Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead. While token compression has been extensively studied in 2D VLMs, existing approaches rely on semantic relevance or attention-based selection that overlook the structured spatial nature of 3D tokens. Moreover, redundancy in 3D representations cannot be resolved by spatial proximity alone, as object-level token imbalance persists even after spatial aggregation. To address this, we propose 3DZip, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence. Experiments on three 3D question answering benchmarks demonstrate that 3DZip consistently outperforms existing compression methods, retaining 94.7% of the original performance with only 128 tokens, achieving a 1.92times faster inference speed.

Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-context inconsistency. In this work, we revisit discrete generative modeling and present Uniform discRete diffuSion with metric pAth (URSA), a simple yet powerful framework that bridges the gap with continuous approaches for the scalable video generation. At its core, URSA formulates the video generation task as an iterative global refinement of discrete spatiotemporal tokens. It integrates two key designs: a Linearized Metric Path and a Resolution-dependent Timestep Shifting mechanism. These designs enable URSA to scale efficiently to high-resolution image synthesis and long-duration video generation, while requiring significantly fewer inference steps. Additionally, we introduce an asynchronous temporal fine-tuning strategy that unifies versatile tasks within a single model, including interpolation and image-to-video generation. Extensive experiments on challenging video and image generation benchmarks demonstrate that URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods. Code and models are available at https://github.com/baaivision/URSA

We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural language questions about videos. We first augment the TVQA dataset with 310.8K bounding boxes, linking depicted objects to visual concepts in questions and answers. We name this augmented version as TVQA+. We then propose Spatio-Temporal Answerer with Grounded Evidence (STAGE), a unified framework that grounds evidence in both spatial and temporal domains to answer questions about videos. Comprehensive experiments and analyses demonstrate the effectiveness of our framework and how the rich annotations in our TVQA+ dataset can contribute to the question answering task. Moreover, by performing this joint task, our model is able to produce insightful and interpretable spatio-temporal attention visualizations. Dataset and code are publicly available at: http: //tvqa.cs.unc.edu, https://github.com/jayleicn/TVQAplus

The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning, which requires a large amount of training data, making it very difficult to achieve zero-shot learning. In this paper, we propose to utilize a pre-trained visual-language model to extract the representative image and text features, and model the relationship between these features through different interaction modules to obtain the interaction feature. In addition, we use this feature to prompt each label to obtain more appropriate text features. Finally, we calculate the similarity between the interaction feature and the text feature for each label to determine the action category. Our experiments on J-HMDB and UCF101-24 datasets demonstrate that the proposed interaction module and prompting make the visual-language features better aligned, thus achieving excellent accuracy for zero-shot spatio-temporal action detection. The code will be available at https://github.com/webber2933/iCLIP.

Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and complex reasoning. For one thing, text-based methods rely on coordinates or index prediction, severely limiting the perceptual capabilities of the model for dense visual objects. Meanwhile, latent token-based methods employ special tokens without inherent spatial references and use a decoding mechanism that lacks thinking steps, weakening high-level reasoning capabilities. Consequently, developing a unified framework that excels in both perception and reasoning remains challenging. To address this, we propose Mixture-of-Thought-Tokens (Motto), a new free-form multimodal grounding method that bridges the perception-reasoning gap, enabling MLLMs to empower diverse, arbitrary grounding queries. Specifically, we introduce Spatially-Grounded Thought Tokenization to explicitly align special tokens with spatial locations for clear spatial correspondence and visual interpretability. We further design a Context-Adaptive Chain-of-Tokens that dynamically switch grounding modes within an interleaved reasoning chain, achieving robust grounding across tasks of varying complexity. In addition, we construct PR-Bench, a new referring expression comprehension benchmark to evaluate the perception-reasoning gap. Extensive experiments demonstrate that Motto achieves state-of-the-art performance across diverse free-form grounding tasks.

We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency. Unlike existing methods that rely on chunk-by-chunk or auto-regressive model with diffusion head, we adopt a diffusion forcing framework to model this time-series generation task under time-varying control events. We find that a straightforward implementation of vanilla diffusion forcing (as proposed for video models) fails to model real motion distributions. We demonstrate that to guarantee modeling the output distribution, the vanilla diffusion forcing must be tailored to: (i) train with a bi-directional attention instead of casual attention; (ii) implement a lower triangular time scheduler instead of a random one; (iii) utilize a continues time-varying way to introduce text conditioning. With these improvements, we demonstrate in the first time that the diffusion forcing-based framework achieves state-of-the-art performance on the streaming motion generation task, reaching an FID of 0.057 on the HumanML3D benchmark. Models, code, and weights are available. https://shandaai.github.io/FloodDiffusion/

Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level representations or calendar tokens have been proposed. However, the optimal approach remains unclear, especially given the diverse statistical distributions of real-world event data, which range from smooth log-normal to discrete, spiky patterns. This paper presents the first empirical study of temporal tokenization for event sequences, comparing distinct encoding strategies: naive numeric strings, high-precision byte-level representations, human-semantic calendar tokens, classic uniform binning, and adaptive residual scalar quantization. We evaluate these strategies by fine-tuning LLMs on real-world datasets that exemplify these diverse distributions. Our analysis reveals that no single strategy is universally superior; instead, prediction performance depends heavily on aligning the tokenizer with the data's statistical properties, with log-based strategies excelling on skewed distributions and human-centric formats proving robust for mixed modalities.

Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-quality images in a few steps. NATs perform generation in a progressive manner, where the latent tokens of a resulting image are incrementally revealed. At each step, the unrevealed image regions are padded with mask tokens and inferred by NAT. In this paper, we delve into the mechanisms behind the effectiveness of NATs and uncover two important patterns that naturally emerge from NATs: Spatially (within a step), although mask and visible tokens are processed uniformly by NATs, the interactions between them are highly asymmetric. In specific, mask tokens mainly gather information for decoding, while visible tokens tend to primarily provide information, and their deep representations can be built only upon themselves. Temporally (across steps), the interactions between adjacent generation steps mostly concentrate on updating the representations of a few critical tokens, while the computation for the majority of tokens is generally repetitive. Driven by these findings, we propose EfficientNAT (ENAT), a NAT model that explicitly encourages these critical interactions inherent in NATs. At the spatial level, we disentangle the computations of visible and mask tokens by encoding visible tokens independently, while decoding mask tokens conditioned on the fully encoded visible tokens. At the temporal level, we prioritize the computation of the critical tokens at each step, while maximally reusing previously computed token representations to supplement necessary information. ENAT improves the performance of NATs notably with significantly reduced computational cost. Experiments on ImageNet-256, ImageNet-512 and MS-COCO validate the effectiveness of ENAT. Code is available at https://github.com/LeapLabTHU/ENAT.

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively encode and understand videos in video-based dialogue systems remains to be solved. In this paper, we investigate a straightforward yet unexplored question: Can we feed all spatial-temporal tokens into the LLM, thus delegating the task of video sequence modeling to the LLMs? Surprisingly, this simple approach yields significant improvements in video understanding. Based upon this, we propose ST-LLM, an effective video-LLM baseline with Spatial-Temporal sequence modeling inside LLM. Furthermore, to address the overhead and stability issues introduced by uncompressed video tokens within LLMs, we develop a dynamic masking strategy with tailor-made training objectives. For particularly long videos, we have also designed a global-local input module to balance efficiency and effectiveness. Consequently, we harness LLM for proficient spatial-temporal modeling, while upholding efficiency and stability. Extensive experimental results attest to the effectiveness of our method. Through a more concise model and training pipeline, ST-LLM establishes a new state-of-the-art result on VideoChatGPT-Bench and MVBench. Codes have been available at https://github.com/TencentARC/ST-LLM.

Nowadays, navigation and ride-sharing apps have collected numerous images with spatio-temporal data. A core technology for analyzing such images, associated with spatiotemporal information, is Traffic Scene Understanding (TSU), which aims to provide a comprehensive description of the traffic scene. Unlike traditional spatio-temporal data analysis tasks, the dependence on both spatio-temporal and visual-textual data introduces distinct challenges to TSU task. However, recent research often treats TSU as a common image understanding task, ignoring the spatio-temporal information and overlooking the interrelations between different aspects of the traffic scene. To address these issues, we propose a novel SpatioTemporal Enhanced Model based on CILP (ST-CLIP) for TSU. Our model uses the classic vision-language model, CLIP, as the backbone, and designs a Spatio-temporal Context Aware Multiaspect Prompt (SCAMP) learning method to incorporate spatiotemporal information into TSU. The prompt learning method consists of two components: A dynamic spatio-temporal context representation module that extracts representation vectors of spatio-temporal data for each traffic scene image, and a bi-level ST-aware multi-aspect prompt learning module that integrates the ST-context representation vectors into word embeddings of prompts for the CLIP model. The second module also extracts low-level visual features and image-wise high-level semantic features to exploit interactive relations among different aspects of traffic scenes. To the best of our knowledge, this is the first attempt to integrate spatio-temporal information into visionlanguage models to facilitate TSU task. Experiments on two realworld datasets demonstrate superior performance in the complex scene understanding scenarios with a few-shot learning strategy.