Video_Caption
-
Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding
2026-08-06 09:15:43Bo Zhang, Wenxin Wang, Feng Chen, Zhihao Zhang, Zixuan Wang, Changsheng Li, Yinjie LeiAbstract
Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, inevitably suffering from misalignment with the target MLLM's intrinsic evidence and failing to accommodate the non-uniform spatiotemporal information density. In this paper, we propose a fine-grained dynamic visual selection framework named EviSelect, grounded in the target MLLM internal attention evidence. Our method efficiently probes visual evidence via sparse prefilling as a structured prior to guide distribution-aware dynamic sampling. Specifically, we efficiently approximate attention maps of the target MLLM using highly compressed visual inputs and sparse attention, well-aligned to the full counterpart. Conditioned on three complementary attention components derived from this prior, we design a lightweight selector that not only precisely locates query-relevant timestamps but also adaptively adjusts the local sampling rate and spatial resolution. To enable evidence-conditioned spatiotemporal sampling, we formulate the selector as a stochastic policy and optimize it via GRPO under a joint accuracy--efficiency reward. By rewarding correct predictions under lower visual cost through group-relative comparisons, our method encourages the policy to allocate computation dynamically according to the information density of each video. Across three long video understanding benchmarks, EviSelect achieves superior performance compared to existing methods while reducing selected visual tokens by about 50\% and achieving a 3.9x end-to-end speedup.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05780
PDF
-
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
2026-08-06 08:33:13Qifeng Zhang, Kaixiang Huang, Heng Dong, Huang Fang, Junting Chen, Junjie Zhu, Yonghang Chen, Zhiyu Zhang, Wei LiAbstract
Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awareness over continuous, long-horizon visual streams. To address this limitation, we introduce the Global-Spatial-Temporal Benchmark (GST-Bench), a VQA benchmark for global spatial intelligence in video understanding, comprising human-verified questions derived from 6,790 minutes of synthetically generated video. It requires models to perform accurate spatial inference from novel viewpoints unseen in the input video and to map egocentric observations onto global top-down images. A comprehensive evaluation of 22 state-of-the-art VLMs exposes a striking gap between models and humans: the strongest zero-shot model attains only 42.68, far below the human score of 79.08. To probe the cause of this gap, we construct GST-Bench-Local and find that models, despite strong local spatial understanding under the same task formulation, still fail to consolidate long-horizon observations into a globally consistent scene representation. We further provide GST-Train, a dataset for global spatial reasoning, as a complementary resource to facilitate future research on this challenge.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05747
PDF
-
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
2026-08-06 07:47:15Wang Chen, Yu Chen, Xiang Wang, Shuai Li, Jinfa Huang, Xiawu ZhengAbstract
Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Since the appropriate frame budget varies with the downstream LMM, reasoning demands, and latency constraints, a practical selector should serve multiple budgets. However, existing methods typically optimize an isolated frame subset for each predefined budget: when the budget changes, previously selected evidence may be replaced rather than progressively augmented. Ranking frames by a fixed score would allow prefix reuse across budgets, but it ignores the distinct roles of different ranking positions. In this paper, we formulate long-video frame selection as a Matryoshka ranking problem: constructing a single priority sequence whose small prefixes concentrate query-conditioned evidence, while progressively larger prefixes preserve this evidence and add broader temporal context. Efficiently constructing such a ranking is itself challenging, as densely sampling long videos and evaluating frame-query relevance incurs substantial overhead. We therefore introduce Matryoshka Evidence-to-Context (MEC) Frame Selection, a training-free framework that builds a reusable sparse video index, discovers candidates through sparse probing and local zooming, and greedily constructs a position-adaptive ranking: early positions emphasize evidence; later positions progressively favor temporal coverage while preserving visual diversity. A single ranking can thus be truncated to any target budget without rerunning the selector. Across four benchmarks and six frame budgets, MEC improves average accuracy over uniform sampling by 3.77 percentage points, matches strong state-of-the-art selectors, and reduces end-to-end selection latency by 47.37-51.19%.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05707
PDF
-
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
2026-08-06 07:46:37Xichen Zhang, Guankai Li, Yinghao Zhu, Shijian Wang, Sitong Wu, Shaozuo Yu, Meng Chu, Yuan Lu, Jiaya JiaAbstract
Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, current evaluations predominantly rely on brief clips and multiple-choice formats. This design allows minimal baselines that process only the last four frames to match or surpass complex streaming models, while answer options also expose language shortcuts. We introduce StreamArena, a benchmark for hour-scale, interactive streaming video understanding. StreamArena contains 243 full-length videos averaging 88.8 minutes and 3,646 rigorously annotated, open-ended question-answer pairs that evaluate real-time perception, historical retrospection, proactive interaction, and multimodal tool utilization. Evaluation across diverse systems exposes a tension between continuous interaction and long-horizon multimodal comprehension. Methods that retain only recent frames cannot recover distant events, methods that convert past observations into text lose visual evidence, and methods that repeatedly compress visual memory struggle to preserve fine-grained details over time. We address this tension with StreamMind, a two-tier architecture that assigns latency-critical interaction and proactive monitoring to independently scheduled frontend workers, while backend workers asynchronously construct persistent multimodal memory and perform historical recall and external search. StreamMind outperforms existing streaming baselines across all four capabilities and reduces query-to-answer latency by reusing persistent state.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05703
PDF
-
Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs
2026-08-06 04:27:59Ziling Huang, Shin'ichi SatohAbstract
Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation makes MLLMs difficult to capture temporally sparse evidence. Existing methods typically rely on uniform sampling, or frame selection, but these strategies usually optimize either broad temporal coverage or local relevance, making it difficult to preserve both global storyline context and fine-grained evidence. We propose VideoRouter(VR) that rethinks long-video understanding as coordinating complementary evidence views rather than selecting a single subset of frames. It first organizes each video into a question-agnostic temporal hierarchy, which partition the video into coarse-to-fine temporally coherent segments. In this hierarchy, upper-level nodes capture broad storyline context and event progression, while lower-level nodes preserve fine-grained local details and evidence-bearing moments. This naturally gives rise to two complementary views: a global view for coverage-oriented reasoning and a local view for detail-oriented evidence recovery. We further introduce a verification-guided router to determine which view is better supported by the selected evidence and select the final answer. We validate the effectiveness of the proposed design through extensive experiments, showing that the verification-guided router effectively coordinates global and local reasoning, and that, on VideoMME, our method outperforms state-of-the-art frame selection methods by 2.9 points, respectively, under the LLaVA-Video-7B backbone. We will release the code.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05592
PDF
-
SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
2026-08-05 17:56:35Yue Zhang, Yingzhao Jian, Yunqiu Xu, Xiaoxiao Sun, Hehe FanAbstract
Understanding 3D scenes is fundamental to embodied intelligence, requiring joint reasoning over heterogeneous information from multiple modalities, including visual and geometric cues. However, the relevance of these modalities often varies across queries. Existing Multimodal Large Language Models (MLLMs) typically rely on fixed modality combinations, overlooking query-dependent modality needs. Such a rigid design can introduce semantic noise from irrelevant modalities while underutilizing more informative ones, leading to wasted computation and diluted reasoning. To address these challenges, this paper proposes SmartMage, a unified MLLM that dynamically orchestrates heterogeneous modalities for semantic-aware 3D scene understanding. Specifically, SmartMage incorporates: (1) a Semantic-guided Modality Adaptive RouTng (SMART) module that selects task-relevant modalities using semantic priors, text-modality alignment, and modality quality; and (2) a Modality-Aware Gating Expert (MAGE) module that leverages modality priors to guide expert activation, fostering adaptive specialization in multimodal reasoning. Empirically, SmartMage achieves state-of-the-art performance across five 3D scene understanding benchmarks, and attains competitive results on RGB-only video understanding benchmarks. In our diagnostic benchmark ScanFacet, tasks are divided into fine-grained semantic categories, enabling analysis of modality combinations preferred by each semantic type. The observed modality-semantic patterns provide further evidence of SmartMage's effectiveness. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.05137
PDF
-
Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos
2026-08-05 15:06:03Yang Wang, Yanan Ma, Yiqi Liu, Zi Yan Chang, Chi-Li Chen, Chia-Yi Hsiao, Tyler Loakman, Aline Villavicencio, Chenghao Xiao, Chenghua LinAbstract
Social media videos often communicate meanings that go beyond their visible actions, captions, or speech. A mundane clip may become humorous, ironic, or satire only through the interaction of multimodal cues and cultural context, making such content a difficult test case for video-language models. In this paper, we introduce \textit{DrivelHub+}, a benchmark for evaluating whether models can infer the implicit, non-linear, and rhetorically layered meanings of social media videos that appear nonsensical on the surface but convey deliberate pragmatic meanings. DrivelHub+ consists of 1,000 videos collected from social media, each annotated with a human-written implicit narrative explanation. Unlike conventional video understanding tasks focused on recognition or description, we present a benchmark that targets contextual multimodal reasoning. We evaluate current video-language models from two perspectives: explanation, where models must explain the pragmatic comprehension of a video in natural language; and representation, where we adapt reasoning-as-retrieval to test whether model representations align videos with their corresponding implicit narratives in both video-to-text and text-to-video retrieval. Our benchmark provides a diagnostic setting for measuring the gap between multimodal perception and pragmatic comprehension, asking whether current models can move beyond describing what is shown to inferring what is meant.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04939
PDF
-
Persistent Object Narratives for Token-Efficient Video Language Models
2026-08-05 13:59:04Junzhe Chen, Siyuan Meng, Xiaojie GuoAbstract
Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-intensive and provide limited explicit structure for linking recurring object evidence across time. We introduce SlotNarrative, a slot-based interface that organizes a video into persistent object narratives represented by compact object-state tokens. Rather than compressing frame-wise features before establishing temporal correspondence, SlotNarrative first groups visual features into object-like slots and then associates recurring observations with clip-level object entries through a lightweight, parameter-free memory that integrates multiple complementary matching cues. Each retained entry is serialized into two token types: an identity token that summarizes persistent object appearance and a set of state tokens that encode segment-level appearance, geometry, visibility, and trajectory information. This design yields an interface of only 144 allocated visual-token positions for a frozen Video-LLM, independent of the number of sampled frames. Across multiple datasets, SlotNarrative achieves a favorable trade-off between accuracy and visual-token count compared with prior compact Video-LLM interfaces. Experimental results establish persistent object narratives as a compact, structured, and temporally organized visual interface for Video-LLMs. Our code will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04866
PDF
-
SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding
2026-08-05 10:39:19Yuqing Feng, Jiawei Ma, Kevin Qinghong Lin, Kun Yuan, Nicolas Padoy, Daniel S. Elson, Anh Nguyen, Stamatia Giannarou, Baoru HuangAbstract
Surgical procedures unfold as structured and recurring clinical events, whose real-time understanding via intraoperative surgical videos is critical for intraoperative decision-making and support. However, existing video understanding methods force a trade-off: autoregressive video-language models support comprehensive reasoning but are not practical for time-sensitive clinical applications, whereas contrastive models offer low latency but struggle with complex scene understanding. Recently, generative retrieval has been explored for general-domain video understanding, but transferring it to surgery is not trivial because near-identical visual appearances may indicate semantically distinct events, and the terminology involved is highly surgery-specific. To this end, we propose SurgNarrator, a new generative retrieval framework tailored for surgical video understanding. We construct a well-curated surgery-centric vocabulary from surgical captions to define a clinically meaningful retrieval space. We then adapt the pre-trained Qwen3-VL-Embedding-8B to learn discriminative clinical representations with a temporally-aware contrastive objective. During inference, a hierarchical, procedure-aware retrieval strategy narrows the search space to the relevant procedure type, delivering fast and effective responses. Our method is comprehensively evaluated on twelve benchmarks in a zero-shot setting and achieves consistent performance gains over state-of-the-art baselines, while reducing output-stage latency by more than two orders of magnitude compared with the generative baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04676
PDF
-
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
2026-08-05 08:51:20Yuqian Fu, Tianwen Qian, Yanjun Li, Yu Li, Kunyu Peng, Xu Zheng, Yongqin Xian, Alessio Tonioni, Yanwei Fu, Xiaoling Wang, Danda Paudel, Federico Tombari, Luc Van Gool, Leyi Wu, Yifan Zhao, Jinjie Zhang, Yinchuan Li, Yingcong Chen, Zixu Li, Zhiwei Chen, Zhiheng Fu, Wenbo Wang, Yupeng Hu, Weili Guan, Liqiang Nie, Takuya Murakawa, Toru Tamaki, Yi Wen, Zhenglin Du, Zhengyang Li, Lingling Li, Licheng Jiao, Wenping MaAbstract
EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scenarios. The first EgoCross Challenge was hosted at the Third EgoVis Workshop at CVPR 2026 and evaluated models on first-person videos from four target domains: surgery, industrial assembly, extreme sports, and animal perspectives. Each test example consists of an egocentric video clip, a question, and four candidate answers, from which the model must select the correct option. This technical report introduces the challenge task, benchmark resources, and two official Codabench tracks. The Source-Limited Track restricts participants to the official baseline model and a small support set, whereas the Open-Source Track permits broader choices of models and training data under rules that prohibit the manual construction of target-domain training data. In total, the challenge received more than 1,500 submissions from over 130 participants, with 19 teams participating in the Open-Source Track and 38 teams in the Source-Limited Track. We further present the official leaderboard results and summarize the winning solutions from both tracks. We hope that this report will serve as a useful technical reference for advancing cross-domain egocentric video understanding. All resources, including the challenge data, baseline implementation, and code released by the winning teams, are made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04589
PDF
-
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
2026-08-05 08:50:23Benlei Cui, Ruize Wang, Junjie Li, Jinhao Chen, Longtao Huang, Yinghao Chen, Yuwen Zhai, Jingqun Tang, Ruijian Jia, Weiwei Wu, Pengfei Sun, Haiwen HongAbstract
Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific information density, content structure, and evidence patterns, causing fixed video-agent designs to incur redundant processing or fail when mismatched. Extending automated agent evolution from text to video is challenging because full long-video execution makes candidate validation expensive, failures propagate across coupled evidence-processing stages, and complex preprocessing, perception tools, and localization strategies make code-level updates difficult to implement reliably. We introduce MetaVideoAgent, a framework that automatically evolves a video agent for a target distribution. It profiles information density and evidence requirements from sparsely sampled frames and associated queries to guide initial design, then compresses localized failures into independently executable minimal validation tasks. It constructs evidence-grounded Gold Paths, audits Student trajectories, aggregates recurring failures across samples, and attributes them to responsible modules. A modular agent representation constrains each update to the primary responsible module and its necessary dependencies. We further introduce VA-EvoBench, covering eight video distributions with separate evolution and held-out splits. With four evolution iterations per distribution, MetaVideoAgent improves every initial agent and raises macro-average accuracy from 38.44% to 51.47%, at an average evolution cost of 3.54M tokens per distribution. The evolved agents outperform the strongest prior fixed-design video agent by 6.39 percentage points while using the fewest tokens and video frames per question among the compared video agents. We will release all code and data to support reproducible research.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04587
PDF
-
Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs
2026-08-05 06:38:11Sareer Ul Amin, Muhammad Ayaz, Muhammad Munsif, Sanghyun SeoAbstract
Video surveillance in public safety, healthcare, and smart environments has made continuous human monitoring routine, raising real risks to personal identity and appearance. Privacy-preserving action recognition (PPAR) tackles the tension between the utility of video understanding and this exposure, and has drawn fast-growing interest. However, existing surveys remain narrow. Most catalog a single mechanism family, predate recent adversarial and hybrid work, or barely address evaluation. The result is a fragmented literature with incompatible threat models, inconsistent metrics, and no shared evaluation standard. We address this with a PRISMA-guided review of 32 peer-reviewed papers (2018--2026) drawn from 885 screened records. Methods sort into five families, namely adversarial learning (52%), skeleton-based (20%), cryptographic (12%), differential privacy (8%), and hybrid (8%), each with distinct privacy, utility, and efficiency trade-offs. Evaluation is the weak point. Only 10% of papers adopt a formal privacy definition, 65% rely on ad-hoc metrics, and 40% report an inconsistently defined cMAP. The trade-offs are steep. Skeleton methods reach about 85% accuracy but drop appearance, adversarial methods hold near 80% utility at moderate privacy (cMAP 0.9 to 0.3--0.5), and differential privacy often falls below 70%. Harder conditions stay under-tested, with fewer than 15% of papers checking cross-dataset generalization, under 10% testing adaptive attackers, and real-time edge deployment nearly untouched. We contribute a two-dimensional privacy-space taxonomy, a formal threat model, a comparative trade-off analysis, the PPAR Unified Evaluation Protocol, and a roadmap centered on benchmark standardization. With this grounding, we argue PPAR can move from prototypes toward deployment, with lessons extending to face recognition and medical imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04501
PDF
-
CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models
2026-08-05 00:20:23Mukhtiar Ali, Harsh Dubey, Sugam Mishra, Chulwoo PackAbstract
Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-level descriptions. We introduce CLIP-CC-Bench, an evaluation suite for long-form video description built from 5 hours of movie content segmented into 90-second clips, each paired with an expert-written paragraph-style reference. The evaluation suite employs an ensemble of five state-of-the-art LLM-based embedding models to increase reliability and mitigate single-model bias, and applies two complementary methodologies: (i) coarse-grained semantic matching and (ii) fine-grained semantic matching to compare model-generated descriptions against CLIP-CC-Bench references. Using this framework, we evaluate 17 state-of-the-art video-language models and report both their Borda-aggregated rankings and their average scores on CLIP-CC-Bench. We further quantify the protocol's internal reliability through inter-judge agreement and bootstrap ranking stability. We release standardized evaluation scripts, model outputs, and aggregation tools at this https URL to support reproducibility. CLIP-CC-Bench provides a practical evaluation framework for long-form video description, filling a gap left by existing short-clip and QA-only benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04302
PDF
-
Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering
2026-08-04 18:23:17Haotian Xia, Zilin Xiao, Junbo Zou, Vicente Ordonez, Hanjie ChenAbstract
Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time. Existing methods typically rely on long textual chain-of-thought rationales, even though many questions can be answered as soon as the relevant object, action, or frame is localized. We propose Dynamic Latent Reasoning (DyLaR), which first grounds a question in a short block of perception latents (continuous hidden states that encode query-relevant visual evidence), and then adaptively decides whether to append reasoning latents (continuous thoughts that reason over this evidence in latent space) before answering. DyLaR learns this behavior by grounding perception latents in verified visual evidence and distilling verified rationales into reasoning latents, followed by reinforcement learning that further refines when to reason. Across nine video benchmarks and four multimodal language model backbones, DyLaR improves average accuracy over same-backbone baselines while generating fewer than 20 tokens per query. On Qwen3-VL-4B, for example, DyLaR improves average accuracy over Qwen3-VL-4B-Thinking from 54.0 to 58.2 while reducing response length from 1,220.7 to 18.5 tokens per query. Ablations further show that grounded perception latents, rationale-supervised reasoning latents, and adaptive routing each improve accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.04124
PDF
-
When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
2026-08-04 16:49:53Ke Li, Jiayu Chen, Maoliang Li, Zihao Zheng, Hailong Zou, Hengyi Zhang, Xuanzhe Liu, Xiang ChenAbstract
Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based methods rely on static one-shot selection with fixed frame budgets and candidate pools, while agent-based schedulers achieve adaptivity through costly multi-round reasoning and interactive search. We propose EcoFrame, a training-free framework for low-overhead query-adaptive visual evidence scheduling. EcoFrame leverages the VLM's inference feedback to determine when to increase the frame budget and where to search for additional candidate evidence. Specifically, entropy-gated budget scheduling uses output uncertainty to stop early when the current evidence is sufficient or progressively expand the frame budget otherwise. Meanwhile, attention-guided candidate proposal converts frame-level attention into a temporal prior, enabling dense local search in informative regions while preserving global coverage when attention is diffuse. Experiments on Video-MME, LongVideoBench, and MLVU demonstrate that EcoFrame achieves a better accuracy--efficiency trade-off across multiple VLM backbones. On Qwen2.5-VL, EcoFrame achieves an average accuracy of 64.4, surpassing BOLT at 63.5, while providing a $1.85\times$ speedup over AKS and BOLT. Compared with the agent-based A.I.R., EcoFrame maintains comparable accuracy with up to a $13.5\times$ inference speedup. Code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03918
PDF
-
Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models
2026-08-04 04:32:48Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda MaoAbstract
Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications. This challenge is further amplified in video processing, where multiple frames must be analyzed simultaneously. Existing token reduction techniques are largely developed for single-image inputs and therefore fail to account for the temporal and inter-frame redundancies present in video sequences. In addition, these methods generally rely on a fixed, uniform pruning ratio applied across all inputs, which is suboptimal because the degree of redundancy can vary significantly between different videos, necessitating content-dependent pruning levels to preserve critical information. To address these limitations, we propose a two-stage adaptive token pruning strategy specifically designed for video processing. In the first stage, we prune out the redundant frames, and in the second stage, token-level pruning is applied within the retained frames. Crucially, the pruning ratio in the second stage is determined adaptively based on the content of each video. This is achieved by analyzing the correlation structure of token embeddings to quantify redundancy, which is used to determine the ratio. Importantly, our method is entirely post-hoc and requires no additional training or fine-tuning, while achieving strong empirical gains; notably, it improves accuracy by +7\% on a video captioning benchmark at 10\% token retention, while reducing computation TFLOPs by 95\%.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03112
PDF
-
GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language Models
2026-08-04 03:51:46Mengjie Zhang, Qihui Zhu, Tao Zhang, Shuangwu Chen, Huihuang Qin, Yu Guo, Shenghao Ye, Zijian Wen, Yunpeng Hou, Dong Jin, Xiaobin Tan, Huasen He, Jian YangAbstract
Video large language models (VideoLLMs) achieve strong video understanding performance, but their inference remains expensive due to the large number of redundant spatio-temporal visual tokens in long videos. Existing token pruning methods alleviate this cost by reducing redundant tokens, yet most of them rely on segment-level local pruning, where videos are partitioned into isolated segments and tokens are selected independently within each segment. Such designs may under-preserve short but semantically dense segments and discard tokens that appear non-salient locally but remain critical from a global perspective. To address this issue, we propose GSTEP (Global Spatio-Temporal Density Pruning), a plug-and-play pruning framework that models video as a continuous spatio-temporal information flow. GSTEP constructs a token-level spatio-temporal density by combining a continuous temporal density, obtained from a smoothed centered frame-level change signal, with intra-frame spatial density, and then performs global token sampling by jointly balancing information density and coverage. Extensive experiments on multiple VideoLLMs and public benchmarks demonstrate that GSTEP consistently achieves strong accuracy-efficiency trade-offs and generalizes well across model architectures and evaluation settings. On LLaVA-OneVision-7B, GSTEP prunes 75% of visual tokens, preserves up to 100.2% of the original average performance across benchmarks, and achieves a 1.17 end-to-end speedup.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03083
PDF
-
CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video Generation
2026-08-04 02:55:10Yizhuo Jia, Jingyun Hua, Yuanxing ZhangAbstract
Text-to-video (T2V) diffusion transformers (DiTs) are trained with detailed video captions, whereas inference often relies on user prompts rewritten by a prompt enhancer (PE). Prior work has improved generation by optimizing the PE, the DiT, or both; some methods have also sought to narrow the training-inference mismatch through shared schemas. Yet even within a shared schema, inference-time PE outputs and DiT training captions may still differ in detail selection, information organization, descriptive granularity, and phrasing. We refer to this residual mismatch as the PE-Caption gap and introduce CAPE-T2V, a two-step Captioner-Anchored Prompt Enhancement framework toward two-sided conditioning alignment in T2V generation. First, CAPE-T2V constructs three types of PE training examples, pairing captioner-generated targets with concise source captions, detailed source captions, or pseudo user prompts derived from those targets. It then fine-tunes the PE to map each input to its paired target. Second, CAPE-T2V fine-tunes the DiT on video-derived captions rewritten by the Anchored PE; the same PE rewrites user prompts at inference. Relative to a baseline using the same caption schema, CAPE-T2V achieves higher aggregate scores on StoryEval, VBench-2.0, and T2V-CompBench across Wan2.2 and LTX-2.3. Further, CAPE-T2V exhibits a smaller PE-Caption gap than the baseline: its DiT fine-tuning captions are closer in distribution to inference-time PE outputs, as measured by squared maximum mean discrepancy in a fixed embedding space. Overall, these results support CAPE-T2V as an effective approach to mitigating the PE-Caption gap. The project is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.03046
PDF
-
PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs
2026-08-03 12:34:31Zhongjie Ba, Shengwang Xu, Peng Cheng, Jinyang Zou, Ting Yu, Zhibo Wang, Zhan QinAbstract
Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities. However, despite their strong performance on general video understanding tasks, current video-language models still struggle to reliably determine whether an observed event conforms to specific physical laws. Existing benchmarks primarily assess the physical quality of generated videos, providing limited support for systematically evaluating and improving the physical-law understanding of Video Large Language Models (VideoLLMs). To address this gap, we introduce PhyCheck, a video question answering dataset organized at two complementary levels of granularity. The coarse-grained subset asks models to determine whether the phenomenon shown in a video conforms to or violates physical laws, while the fine-grained subset further examines whether models can capture physical details responsible for the violation or compliance. We use these subsets as structured supervision to improve physical understanding. In addition, the dataset contains a diagnostic subset with external causal context that reveal hidden factors affecting physical plausibility, assessing whether models can recalibrate their judgments accordingly. Experiments with Fine-tune Qwen2.5-VL show that training with the proposed data substantially improves the understanding of physical-consistency, while evaluations in the diagnostic subset reveal that current models still have difficulty incorporating additional causal conditions into their decisions. These findings highlight the gap between recognizing surface-level inconsistencies and understanding underlying physical mechanisms, and provide a foundation for evaluating and improving physical understanding in Video-LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02150
PDF
-
RSVideo: Are Your Vision-Language Models Ready for Remote Sensing Videos?
2026-08-03 10:34:42Hongjie Zhou, Shiqin Wang, Haoyang Chen, Haonan Guo, Di Wang, Juhua Liu, Fu Lin, Yong LuoAbstract
Remote-sensing videos enable real-time observation of changes in target attributes, short-term activities, and scene evolution. They record motion, actions, interactions, and scene changes that cannot be captured by isolated images. Existing models primarily target single images or discrete temporal observations spanning a long time range. However, a unified evaluation setting for assessing vision-language models on continuous remote-sensing video understanding remains lacking. We introduce RSVideo-10K, a remote-sensing video dataset comprising 10,773 instances, 1.47 million frames, and 17.02 hours of footage, containing both unmanned aerial vehicles and satellite platforms. Its fixed evaluation benchmark, RSVideo-Bench, contains 2,731 test instances and evaluates two complementary aspects of remote-sensing video understanding: L1 Perception and L2 Reasoning, spanning seven capability groups and 17 tasks. Evaluations show that current vision-language models still struggle to recover small local evidence, track short-lived states, and use scene-constrained spatial relations. Based on this analysis, we further propose RSVideo, a reinforcement learning framework for small-target spatiotemporal focusing that selects question-relevant regions across frames and suppresses redundant background tokens. RSVideo achieves a maximum absolute improvement of 9.01% with InternVL3.5-14B and attains the highest accuracy of 40.63% with Qwen3.6-27B across 26 open-source vision-language this http URL will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.02039
PDF
