Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge such as object motion, 3D geometry, and physical cues. In contrast, masked video modeling (MVM) directly exploits spatiotemporal structures but trails text-supervised methods on general tasks.We find this gap arises from overlooked architectural issues: pixel-level reconstruction struggles with convergence and its low-level requirement often conflicts with semantics, while latent prediction often encourages shortcut learning.To address these, we disentangle the traditional encoder-decoder design into an Encoder-Predictor-Decoder (EPD) framework, where the predictor acts as a latent world model, and propose InternVideo-Next, a two-stage pretraining scheme that builds a semantically consistent yet detail-preserving latent space for this world model.First, conventional linear decoder in pixel MVM enforces the predictor's output latent to be linearly projected to, thus separable in pixel space, causing the conflict with semantic abstraction.Our Stage 1 proposes a conditional diffusion decoder and injects clean image-level semantic priors to enhance semantics and convergence, thus bridging pixel-level fidelity with high-level semantic abstraction.Stage 2 further learns world knowledge by predicting frozen Stage 1 targets within this space, mitigating shortcut learning.Trained on public, unlabeled videos, InternVideo-Next achieves state-of-the-art results across benchmarks and provides a scalable path toward general video representation learning.
论文检索
输入标题、作者或关键词，从 2,006 篇学术成果中精准定位
Adapting image-pretrained backbones to video typically relies on time-domain adapters tuned to a single temporal scale. Our experiments show that these modules pick up static image cues and very fast flicker changes, while overlooking medium-speed motion. Capturing dynamics across multiple time-scales is, however, crucial for fine-grained temporal analysis (i.e., opening vs. closing bottle).To address this, we introduce Frame2Freq -- a family of frequency-aware adapters that perform spectral encoding during image-to-video adaptation of pretrained Vision Foundation Models (VFMs), improving fine-grained action recognition. Frame2Freq uses Fast Fourier Transform (FFT) along time and learns frequency-band specific embeddings that adaptively highlight the most discriminative frequency ranges. Across five fine-grained activity recognition datasets, Frame2Freq outperforms prior PEFT methods and even surpasses fully fine-tuned models on four of them. These results provide encouraging evidence, that frequency analysis methods are a powerful tool for modeling temporal dynamics in image-to-video transfer.
TimeRipples: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
PDF ↗The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they suffer from substantial inference delay due to self-attention. While prior studies have focused on reducing redundant computations in self-attention, they often overlook the inherent spatio-temporal correlations in video streams and directly leverage sparsity patterns from large language models to reduce attention computations. In this work, we take a principled approach to accelerate self-attention in vDiTs by leveraging the spatio-temporal correlations in the latent space. We show that the attention patterns within vDiT are primarily due to the dominant spatial and temporal correlations at the token channel level. Based on this insight, we propose a lightweight and adaptive reuse strategy that approximates attention computations by reusing partial attention scores of spatially or temporally correlated tokens along individual channels. We demonstrate that our method achieves significantly higher computational savings (85%) compared to state-of-the-art techniques over 4 vDiTs, while preserving almost identical video quality (<0.06% loss on VBench).
Understanding egocentric videos plays a vital role for embodied intelligence. Recent multi-modal large language models (MLLMs) can accept both visual and audio inputs. However, due to the challenge of obtaining text labels with coherent joint-modality information, whether MLLMs can jointly understand both modalities in egocentric videos remains under-explored. To address this problem, we introduce EgoAVU, a scalable data engine to automatically generate egocentric audio-visual narrations, questions and answers. EgoAVU enriches human narrations with multimodal context and generates audio-visual narrations through cross-modal correlation modeling. Token-based video filtering and modular, graph based curation ensure both the data diversity and quality. Leveraging EgoAVU, we construct EgoAVU-Instruct - a large scale training dataset of 3M samples, and EgoAVU-Bench - a manually verified evaluation split of 3K samples. EgoAVU-Bench clearly reveals the limitation of existing MLLMs: they bias heavily towards visual signals, often neglecting audio cues or failing to correspond audio with the visual source. Finetuning MLLMs on EgoAVU-Instruct effectively solves this issue, enabling up to 113% performance improvement on EgoAVU-Bench. Such benefit can also transfer to other benchmarks such as EgoTempo and EgoIllusion, achieving up to 28% relative performance gain. Project page: https://cs20s030.github.io/EgoAVU/
Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence reflects speculation, answering after it has passed reduces real-time utility. To capture this behavior, we introduce a readiness-aware formulation of streaming video understanding with the **Answer Readiness Score (ARS)**, a timing-aware objective with asymmetric early and late penalties. When combined with correctness, ARS defines an effective accuracy that measures not just whether a model is right, but whether it answers at the appropriate moment. Building on this formulation, we introduce **StreamReady**, a framework to unify temporal reasoning with on-time answering through a lightweight readiness mechanism that decides if sufficient evidence has been observed before responding. To evaluate this capability, we further introduce **ProReady-QA**, a benchmark with annotated answer evidence windows and proactive multi-turn questions across local and global contexts. StreamReady achieves superior performance on ProReady-QA, and consistently outperforms prior methods across eight additional streaming and offline long-video benchmarks, demonstrating robust and broadly generalizable video understanding capability.
With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding i.e. image-to-video transfer learning has become a dominant paradigm. To achieve superior performance, it raises as an effective strategy among recent advances to employ Mixture-of-Experts (MoE) to enhance VLMs' temporal modeling capabilities. However, conventional MoE designs suffer from expert homogenization, where all experts act as identical generalists, inefficiently learning spatio-temporal features from undifferentiated video streams.To overcome this problem, we propose VidPrism, a novel heterogeneous temporal Mixture-of-Experts framework. VidPrism pioneers a division of labor by deploying functionally specialized experts, each assuming a role ranging from spatial understanding to temporal modeling.To feed these specialists appropriately, we introduce a content-aware, multi-rate sampling module that dynamically generates streams ranging from semantically rich to motion-focused representations, providing specialized inputs for experts.Furthermore, a dynamic, bidirectional fusion mechanism enables synergistic information exchange between these pathways, leading to a comprehensive video representation. Extensive experiments on various video recognition benchmarks demonstrate that VidPrism achieves state-of-the-art performance and effectively fosters expert specialization.
Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by 3.3x, eg., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.
Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training protocols make them ill-suited for streaming settings where frames arrive sequentially and future observations are inaccessible. We diagnose a core limitation of current Video-LLMs, namely Time-Agnosticism, in which videos are treated as an unordered bag of evidence rather than a causally ordered sequence, yielding two failures in streams: temporal order ambiguity, in which the model cannot follow or reason over the correct chronological order, and past-current focus blindness where it fails to distinguish present observations from accumulated history. We present WeaveTime, a simple, efficient, and model-agnostic framework that first teaches order and then uses order. We introduce a lightweight Temporal Reconstruction objective--our Streaming Order Perception enhancement--that instills order-aware representations with minimal finetuning and no specialized streaming data. At inference, a Past-Current Dynamic Focus Cache performs uncertainty-triggered, coarse-to-fine retrieval, expanding history only when needed. Plugged into exsiting Video-LLM without architectural changes, WeaveTime delivers consistent gains on representative streaming benchmarks, improving accuracy while reducing latency. These results establish WeaveTime as a practical path toward time-aware stream Video-LLMs under strict online, time-causal constraints. Code and weights will be made publicly available.
With the rapid development of Multimodal Large Language Models (MLLMs), their potential in Micro-Action understanding, a vital role in human emotion analysis, remains unexplored due to the absence of specialized benchmarks. To tackle this issue, we present MA-Bench, a benchmark comprising 1,000 videos and a three-tier evaluation architecture that progressively examines micro-action perception, relational comprehension, and interpretive reasoning. MA-Bench contains 12,000 structured question-answer pairs, enabling systematic assessment of both recognition accuracy and action interpretation. The results of 23 representative MLLMs reveal that there are significant challenges in capturing motion granularity and fine-grained body-part dynamics. To address these challenges, we further construct MA-Bench-Train, a large-scale training corpus with 20.5K videos annotated with structured micro-action captions for fine-tuning MLLMs. The results of Qwen3-VL-8B fine-tuned on MA-Bench-Train show clear performance improvements across micro-action reasoning and explanation tasks. Our work aims to establish a foundation benchmark for advancing MLLMs in understanding subtle micro-action and human-related behaviors. Project Page: https://MA-Bench.github.io
Efficiently understanding long-form videos remains a fundamental challenge for Multimodal Large Language Models (MLLMs). In this paper, we present MLLM-Sampler Joint Evolution (MSJoE), a novel framework that jointly evolves the MLLM and a lightweight key-frame sampler for efficient long-form video understanding. MSJoE builds upon a key assumption that only a small subset of key-frames is truly informative for answering each question to a video. Specifically, MSJoE first reasons out several queries, which describe diverse visual perspectives relevant to the question. Then, these queries interact with a frozen CLIP model to produce a query-frame similarity matrix. Finally, A lightweight sampler predicts key-frame sampling weights from this matrix, selecting informative frames, which are then fed into the MLLM for answer generation. Both the MLLM and sampler are jointly optimized through reinforcement learning, enabling co-adaptation of query-reasoning, frame-sampling, and key-frame understanding. A new long-video QA dataset containing 2.8k videos with 7k question-answer pairs is collected to support the training process. Extensive experiments on VideoMME, LongVideoBench, LVBench, and MLVU show that MSJoE achieves 8.0% accuracy gain upon the base MLLM, and 1.1% higher accuracy than strongest baseline method.
CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning
PDF ↗Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic environments. Despite its promising potential, EVR encounters significant challenges stemming from the diversity of complex instructions and the intricate spatiotemporal dynamics in long-term egocentric videos. Prior solutions either employ Large Language Models (LLMs) over static video captions, which often omit critical visual details, or rely on end-to-end Vision-Language Models (VLMs) that struggle with stepwise compositional reasoning. Considering the complementary strengths of LLMs in reasoning and VLMs in perception, we propose CLiViS. It is a novel training-free framework that leverages LLMs for high-level task planning and orchestrates VLM-driven open-world visual perception to iteratively update the scene context. Building on this synergy, the core of CLiViS is a dynamic Cognitive Map that evolves throughout the reasoning process. This map constructs a structured representation of the embodied scene, bridging low-level perception and high-level reasoning. Extensive experiments across multiple benchmarks demonstrate the effectiveness and generality of CLiViS, especially in handling long-term visual dependencies. Code is available at https://github.com/Teacher-Tom/CLiViS.
Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific metrics and an implicit assumption of spatiotemporal separability. Under extremely low retention ratios, however, such approaches often result in unbalanced allocation and loss of visual evidence essential for question answering. We reformulate token compression as a spatiotemporal allocation task within a global token retention pool. We propose a unified selection mechanism that integrates attention weights and semantic similarity to globally select tokens with high contribution and low redundancy. Unselected tokens are merged via clustering and refilled, preserving information integrity. Inside the LLM, we further introduce text-aware merging to perform secondary compression based on query relevance. Without requiring retraining, our method serves as a plug-and-play module compatible with existing Video-LLMs. Experiments show that retaining only about 2% of visual tokens preserves 90.1% of baseline performance across multiple benchmarks, while reducing FLOPs to roughly 2.6%. These benefits generalize across diverse backbones, decreasing end-to-end inference latency and memory consumption. Our unified spatiotemporal token compression strategy establishes the state-of-the-art in video understanding under ultra-low token retention.
Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability
PDF ↗Large language models (LLMs) often generate self-contradictory outputs, which severely impacts their reliability and hinders their adoption in practical applications. In video-language models (Video-LLMs), this phenomenon recently draws the attention of researchers. Specifically, these models fail to provide logically consistent responses to rephrased questions based on their grounding outputs. However, the underlying causes of this phenomenon remain underexplored. In this work, we adopt an interpretability-driven approach to analyze, statistically summarize, and intervention the potential factors of the phenomenon. We find that one of the primary reasons for the inconsistency in responses lies in the inability of cross-modal attention heads to effectively distinguish video tokens across different timestamps. To address this, we propose an attention enhancement method called **T**emporally **C**onditioned **A**ttention **S**harpening (**TCAS**), which constructs an enhancement objective based on attention distinctions to enhance the model's temporal resolution capability, thereby improving its temporal understanding logic consistency. Experimental results demonstrate that our method significantly enhances the temporal logic consistency of Video-LLMs. Further analyses reveal that our method indeed improves the temporal discriminability of attention heads, validating our conclusions. Additionally, our method even achieves performance improvements in general video temporal grounding tasks, suggesting that temporal logic consistency is an important factor in temporal understanding.
This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D priors or geometric constraints. However, these methods often struggle to maintain reconstruction accuracy and consistency over long sequences due to limited memory capacity and the inability to effectively capture global contextual cues. In contrast, humans can naturally exploit the global understanding of the scene to inform local perception. Motivated by this, we propose a novel neural global context representation that efficiently compresses and retains long-range scene information, enabling the model to leverage extensive contextual cues for enhanced reconstruction accuracy and consistency. The context representation is realized through a set of lightweight neural sub-networks that are rapidly adapted during test time via self-supervised objectives, which substantially increases memory capacity without incurring significant computational overhead. The experiments on multiple large-scale benchmarks, including the KITTI Odometry [??] and Oxford Spires [??] datasets, demonstrate the effectiveness of our approach in handling ultra-large scenes, achieving leading pose accuracy and state-of-the-art 3D reconstruction accuracy while maintaining efficiency. Code will be available at https://zju3dv.github.io/scal3r.
LayoutAD: Exploring Semantic-Geometric Misalignment Reasoning for Scene Layout Anomaly Detection
PDF ↗Visual anomaly detection is vital for quality control applications by identifying deviations from normal patterns. Previous structural or logical anomaly detection methods mainly focus on pixel-level deviations like texture defects and reconstruction errors, ignoring the object-level structural and contextual inconsistencies. These overlooked layout anomalies remain critical yet underexplored, e.g., factually defective hallucinations appeared in generative text-to-image models. Based on the above observation, in this paper, we introduce scene layout anomaly detection, a new task that predicts an object-level anomaly map from the input image to reveal the semantic plausibility and geometric consistency of each object in the scene. Specifically, we propose LayoutAD, an unsupervised learning framework that constructs semantic and geometric graphs to jointly reason over semantic-geometric misalignment among objects. Under this formulation, we are able to detect diverse layout deviations, including object attribute implausibilities and relationship mismatches. Extensive experiments show that LayoutAD outperforms baselines qualitatively and quantitatively across various scenarios, benefiting scene understanding and generation applications like video anomaly detection and self-corrected image generation.
Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter, whether observing sparse moving dots, textured surfaces, or naturalistic scenes. In contrast, existing computer vision systems lack a unified approach that works across these diverse settings. Inspired by principles of human perception, we propose a generative model that hierarchically groups low-level motion and appearance features into particles (small Gaussians representing local matter), and groups particles into clusters capturing coherently and independently moveable physical entities. We develop a hardware-accelerated inference algorithm based on parallelized block Gibbs sampling to recover stable particle motion and groupings. Our model operates on different kinds of inputs (random dots, stylized textures, or naturalistic RGB video), enabling it to work across settings where biological vision succeeds but existing computer vision approaches do not. We validate this unified framework across three domains: on 2D random dot kinematograms, our approach captures human object perception including graded uncertainty across ambiguous conditions; on a Gestalt-inspired dataset of camouflaged rotating objects, our approach recovers correct 3D structure from motion and thereby accurate 2D object segmentation; and on naturalistic RGB videos, our model tracks the moving 3D matter that makes up deforming objects, enabling robust object-level scene understanding. This work thus establishes a general framework for motion-based perception grounded in principles of human vision.
Recent advances in multimodal large language models (LLMs) have enabled unified reasoning across images, audio, and video, but extending such capability to brain imaging remains largely unexplored. Bridging this gap is essential to link neural activity with semantic cognition and to develop cross-modal brain representations. To this end, we present fMRI-LM, a foundational model that bridges functional MRI (fMRI) and language through a three-stage framework. In Stage 1, we learn a neural tokenizer that maps fMRI into discrete tokens embedded in a language-consistent space. In Stage 2, a pretrained LLM is adapted to jointly model fMRI tokens and text, treating brain activity as a sequence that can be temporally predicted and linguistically described. To overcome the lack of natural fMRI-text pairs, we construct a large descriptive corpus that translates diverse imaging-based features into structured textual descriptors, capturing the low-level organization of fMRI signals. In Stage 3, we perform multi-task, multi-paradigm instruction tuning to endow fMRI-LM with high-level semantic understanding, supporting diverse downstream applications. Across various benchmarks, fMRI-LM achieves strong zero-shot and few-shot performance, and adapts efficiently with parameter-efficient tuning (LoRA), establishing a scalable pathway toward a language-aligned, universal model for structural and semantic understanding of fMRI.
We present the first systematic analysis of multimodal large language models (MLLMs) in personalized question-answering requiring ego-grounding - the ability to understand the camera-wearer in egocentric videos. To this end, we introduce MyEgo, the first egocentric VideoQA dataset designed to evaluate MLLMs' ability to understand, remember, and reason about the camera wearer. MyEgo comprises 541 long videos and 5K personalized questions asking about "my things", "my activities", and "my past". Benchmarking reveals that competitive MLLMs across variants, including open-source vs. proprietary, thinking vs. non-thinking, small vs. large scales all struggle on MyEgo. Top closed- and open-source models (e.g., GPT-5 and Qwen3-VL) achieve only 46% and 36% accuracy, trailing human performance by near 40% and 50% respectively. Surprisingly, neither explicit reasoning nor model scaling yield consistent improvements. Models improve when relevant evidence is explicitly provided, but gains drop over time, indicating limitations in tracking and remembering "me" and "my past". These findings collectively highlight the crucial role of ego-grounding and long-range memory in enabling personalized QA in egocentric videos. We hope MyEgo and our analyses catalyze further progress in these areas for egocentric personalized assistance.
The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understanding are limited by the inherent disconnect between reasoning and perception: they rely on static, pre-processed information and cannot actively seek raw evidence from video as their understanding evolves. To address this, we introduce LensWalk, a flexible agentic framework that empowers a Large Language Model reasoner to control its own visual observation actively. LensWalk establishes a tight reason-plan-observe loop where the agent dynamically specifies, at each step, the temporal scope and sampling density of the video it observes. Using a suite of versatile, Vision-Language Model based tools parameterized by these specifications, the agent can perform broad scans for cues, focus on specific segments for fact extraction, and stitch evidence from multiple moments for holistic verification. This design allows for progressive, on-demand evidence gathering that directly serves the agent's evolving chain of thought. Without requiring any model fine-tuning, LensWalk delivers substantial, plug-and-play performance gains on multiple model recipes, boosting their accuracy by over 5% on challenging long-video benchmarks like LVBench and Video-MME. Our analysis reveals that enabling an agent to control how it sees is key to unlocking more accurate, robust, and interpretable video reasoning.
We present Ego-1K, a large-scale, time-synchronized collection of egocentric multiview videos designed to advance neural 3D video synthesis, dynamic scene understanding, and embodied perception. The dataset contains nearly 1,000 short egocentric videos taken with a custom rig with 12 synchronous cameras surrounding a VR headset worn by the user. Scene content focuses on hand motions and hand-object interactions in different settings. We describe rig design, data processing, and calibration. Our dataset enables new ways to benchmark egocentric scene reconstruction methods. We believe this is an important area of research as smart glasses with multiple cameras become omnipresent. Our experiments demonstrate that our dataset presents unique challenges for existing 3D and 4D novel view synthesis methods due to high disparities and image motion caused by close dynamic objects and rig egomotion. Our dataset supports future research in this challenging domain, enabling 4D world creation and sharing.