Video_Caption
-
EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
2026-08-12 22:20:29Le Zhang, Ke SunAbstract
Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in existing systems: indices built from context-poor captions are unreliable for agentic search, while retrieval ignores a question's temporal intent. To address both bottlenecks, we introduce EgoCITE (Egocentric Context-augmented Indexing and Time-aware Evidence retrieval), a long-horizon agentic memory framework for egocentric QA. EgoCITE comprises three components. EgoScheme uses local multimodal context to turn fragmentary video captions and speech transcripts into self-contained atomic memory indices. EgoIndex organizes complementary action, activity, utterance, and conversation representations into searchable multi-view memory indices at multiple granularities. EgoRetrv combines semantic search with question-conditioned temporal relevance scoring and curation of retrieved evidence. We evaluate EgoCITE on EgoLifeQA, EgoMem, and EgoR1-Bench in terms of answer accuracy and target-event retrieval alignment. EgoCITE improves accuracy over agentic memory baselines by at least 4.4--14.2\% while achieving 36$\times$ lower cost than long-context LLM agents.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12627
PDF
-
StrAD: A Streaming Method and Benchmark for Audio Description Generation for Long-form Videos
2026-08-12 19:39:17Julian Spravil, Sebastian Houben, Sven BehnkeAbstract
Visual content is the dominant medium of communication, yet without audio descriptions (ADs), it remains inaccessible to blind and low-vision people. ADs narrate context-relevant visual events during natural audio pauses. Manually creating ADs is expensive, limiting coverage to a small fraction of available content. Most existing automatic AD generation methods frame the task as video clip captioning, requiring ground-truth timestamps and additional context cues such as character databases. Current benchmarks reinforce this framing, consisting of short video segments paired with automatic or task-mismatched annotations. We introduce StrAD, a benchmark for long-form AD generation on full-length videos spanning diverse genres such as movies, documentaries, short films, performances, and video games. We reformulate AD generation as streaming dense video captioning. Our approach processes full-length videos with a sliding window, inserting ADs into existing transcripts without ground-truth timestamps, and supports both fine-tuned models and zero-shot prompting of vision-language models. On the segment-level task with given timestamps, our fine-tuned StrAD-FT sets the state of the art on CMD-AD with 36.3 CIDEr (+10.0 over Shot-by-shot), establishes a reference point on StrAD (51.0 CIDEr), and remains competitive on MAD-Eval at 24.9 CIDEr. On the full-video streaming task, StrAD-FT reaches a SODA score of 2.4 against 1.1 for our zero-shot baseline StrAD-Zero, though both exhibit limitations in temporal localization and narrative coherence. While prior work has tackled full-video AD generation in an offline, multi-stage fashion, ours is the first streaming approach, generating ADs on the fly without ground-truth timestamps. StrAD makes progress on full-video AD generation measurable, a prerequisite for scaling accessibility.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12549
PDF
-
VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding
2026-08-12 03:24:44Fan Zhang, Guangming Yao, Jinyang Wu, Hao Wu, Zheng Lian, Xinyu Geng, Jingdong Chen, Yi Yuan, Pheng-Ann HengAbstract
Video understanding is a fundamental task for evaluating the capabilities of multimodal large language models (MLLMs). However, existing leading models have already achieved approximately 90% accuracy on the Video-MME leaderboard, suggesting that conventional single-turn video understanding tasks are becoming increasingly saturated and insufficient for assessing the intelligence of advanced MLLMs. Towards this end, we introduce VideoGAIA, an agentic video understanding benchmark for general artificial intelligence (AI) assistants. Moving beyond one-shot video question answering, VideoGAIA formulates video understanding as a multi-turn, tool-augmented interaction process, where models must iteratively perceive videos, invoke external tools, gather complementary information, and integrate multimodal evidence across turns. VideoGAIA contains 271 model-human co-designed tasks covering diverse and complex real-world scenarios. Each video-question-answer instance is independently verified by three human experts to ensure both correctness and appropriate difficulty. All evaluated MLLMs, including frontier models such as GPT-5.5 and Kimi-K3, achieve less than 60% accuracy on VideoGAIA, highlighting its value as a high-quality and timely benchmark for evaluating next-generation MLLMs. We hope that VideoGAIA will facilitate the transition from conventional video understanding toward agentic video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14718
PDF
-
Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning
2026-08-11 14:57:44Liangyu Fu, Junbo Wang, Yuke Li, Ya Jing, Xuecheng Wu, Zhiyong WangAbstract
Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap between the training (text-only) and the inference (video-only). Previous works attempt to bridge the gap through simple linear transformations. However, the inherent gap between text and video makes cross-modal representation space alignment insufficient, resulting in inaccurate sentences. To address this issue, we propose a novel zero-shot video captioning framework (WSV) consisting of two training stages, which first generates corresponding synthetic video latent representations via a pretrained text-to-video generation model. To strengthen the fidelity of the latent representations, we propose a polisher capable of bridging the gap between real and synthetic video distributions. Subsequently, we design a prompter that conditions GPT-2 on the polished latent representations to generate the captions in the second training stage. During inference, an input video is encoded by a pretrained 3D Causal VAE and then fed directly into the prompter, which in turn guides GPT-2 to produce the final caption. Experimental results conducted on MSVD, MSR-VTT, and VATEX datasets demonstrate that our proposed method achieves scores of 52 and 95.7 on the B@4 and CIDEr metrics, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11013
PDF
-
StreamFlow: Dynamic Memory Flows for Streaming Video Understanding
2026-08-11 14:19:03Muxin Fu, Yifan Zhang, Wentao Zhang, Fangming Guo, Qian Chen, Guibin Zhang, Shuicheng Yan, Bo AnAbstract
Streaming video understanding requires multimodal large language models (MLLMs) to preserve relevant evidence from continuously evolving streams under strict causality and bounded memory. Yet existing paradigms remain limited: model-based methods require intrusive backbone updates, while memory-based methods expend substantial visual-encoding computation on temporally redundant content and rely on rigid access to visual history. To address these limitations, we introduce StreamFlow, an efficient visual memory framework that enables dynamic, on-demand access to historical visual information. StreamFlow combines a lightweight, dynamics-aware mid-term memory that filters temporal redundancy before visual encoding with a latent long-term memory that consolidates historical video content into visual latents accessible to subsequent reasoning. During generation, an attention-guided retrieval mechanism injects relevant visual latents when the model's reliance on visual evidence weakens. StreamFlow achieves state-of-the-art streaming video understanding performance, reaching 67.73% overall accuracy on StreamingBench, while also delivering strong performance on offline long-video benchmarks. Relative to the vanilla setting, it improves the visual attention score (VAS) by 59.1% while reducing end-to-end latency and peak memory by 50.4% and 21.1%, respectively, enabling more visually grounded and efficient reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10949
PDF
-
Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models
2026-08-11 12:34:41Kiet T. Nguyen, Hanbo Shim, Jinwoo Kim, Seunghoon HongAbstract
Vision-language models (VLMs) have achieved strong image and video understanding, yet their visual-spatial representations remain geometrically fragile, leading to failures in spatial reasoning needed for embodied AI, robotics, and autonomous driving. Prior approaches to geometry grounding either fine-tune VLMs on spatial question answering, which can perpetuate spurious visual representations, or fuse features from large geometry-grounded vision models, which substantially increases model size at inference. Knowledge distillation from geometry-grounded vision models offers an alternative, but directly matching multi-view teacher features can disrupt the pretrained alignment between visual and textual representations, degrading object- and language-semantic capabilities. We propose multi-view relational distillation (MVRD), which distills patch-wise cosine similarities across views instead of the teacher features themselves. These relations encode geometric correspondences adequate for spatial understanding, while leaving the student representation underdetermined, allowing it to remain close to its pretrained vision- language space. Across representative VLMs, MVRD improves visual-spatial reasoning, outperforming supervised fine-tuning and feature distillation while approaching feature fusion methods with considerably fewer added parameters and lower latency. We show that MVRD makes visual representations more geometric while retaining language alignment, and generalizes to 3D scene understanding tasks such as object grounding, dense captioning, and question answering.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10864
PDF
-
FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding
2026-08-11 10:22:08Fufangchen Zhao, Jinhu Fu, Jiachen Lei, Jiahong Wu, Xiangxiang Chu, Danfeng YanAbstract
Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ) benchmarks inadvertently leak target events through their questions and candidate options. This reduces the core challenge from active discovery to text-guided verification. In this paper, we present FADE, an effective training framework for counterfactual discovery and explanation. Our method is built on an evidence-first, two-stage training paradigm. First, evidence-internalized supervised fine-tuning grounds the model's predictions in decisive visual anomalies. Second, we apply a fading-anchor reinforcement learning strategy that progressively removes textual guidance, compelling the model to independently discover and explain evidence. To rigorously evaluate this capability, we also introduce an effective pipeline that converts existing MCQ datasets into aligned MCQ, open-ended question answering (OQA), and captioning tasks without requiring additional data curation. Our simple approach yields strong results. Using Qwen3-VL-8B as the baseline, FADE achieves state-of-the-art strict paired scores across all three tasks on DualityVidQA-test and IPV-Bench, outperforming GPT-5.6. In specific, when transitioning from constrained MCQs to unconstrained OQA and captioning, our model demonstrates remarkable robustness. Its performance retention is 90.4% and 67.4% on DualityVidQA-test-substantially higher than the 48.1% and 30.7% retained by GPT-5.6. We hope this simple framework can serve as a solid baseline for future research in unconstrained counterfactual video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10764
PDF
-
REFRAMED: Towards Realistic Audio Description Generation for Movies
2026-08-10 15:55:56Igor Sterner, Mirella Lapata, Alex Lascarides, Frank KellerAbstract
Audio Description (AD) is a verbal narration of key visual content in videos, enabling access for visually impaired audiences. Unlike standard video captioning, AD is a structured editorial task: descriptions must be inserted into gaps in dialogue and must convey only what is needed to understand the narrative being told. However, existing approaches formulate AD generation in an artificial setting where both the content and timing of descriptions are pre-specified, reducing the task to clip-level captioning. They further rely on noisy transcription and alignment pipelines, and lack the rich parallel data required for modeling narrative context. We introduce a new formulation of AD generation in which models must jointly decide what to describe and when to do it. To support this, we present REFRAMED, a high-quality dataset of 2,023 videos that span 3,302 scenes from 206 movies, with professional AD transcripts (both American and British versions), professional subtitles and aligned screenplays. We also provide a manually curated challenge set that pairs full movies with multiple AD references, together with evaluation protocols that leverage dialogue gaps and multi-reference comparisons. Experiments with state-of-the-art AD systems and multimodal LLMs show that they outperform trivial baselines but fall far short of expert human performance. Our dataset and benchmark establish a new foundation for research on video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09765
PDF
-
NBA_Streaming: A Large-Scale Benchmark for Fine-Grained Basketball Commentary Generation in Continuous Streams
2026-08-10 07:15:09Lifang Wu, Yuyang Wu, Yangdong Gao, Fengyu Liu, Ya Jing, Liang WangAbstract
Live basketball commentary generation requires determining when an event is sufficiently observable and describing it before subsequent events unfold. However, existing methods are primarily designed for pre-segmented clips or complete videos, making them unsuitable for continuous streams. Existing datasets also provide limited supervision for player identities, fine-grained actions, event attributes, and coherent event chains, restricting the factual richness of generated commentary. To address these limitations, we introduce NBA_Streaming, a large-scale benchmark for online fine-grained basketball commentary generation. It contains 307 hours of basketball broadcasts and approximately 35K temporally aligned events, with annotations of event boundaries, player identities, fine-grained actions, event chains, and natural-language commentary. By moving from isolated clips to continuous streams, NBA_Streaming enables unified evaluation of event localization, response reliability, factual grounding, and commentary quality under causal constraints. We further propose a causal two-stage framework that combines completion-first localization with ball-centric semantic grounding, enabling the system to identify complete events from observed streams and organize scene, event, identity, and action cues for commentary generation. Extensive experiments reveal the difficulty of NBA_Streaming, where existing baselines struggle with online timing, factual grounding, and fine-grained description. Our framework consistently improves over strong alternatives, while the remaining gap highlights NBA_Streaming as a valuable benchmark for streaming sports video understanding and generation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09200
PDF
-
VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models
2026-08-09 10:09:11Dong Xing, Jiaxin Chen, Hang Yang, Peixun Liu, Qiushi Yang, Yuqing WangAbstract
Large vision-language models (LVLMs) have demonstrated strong performance in open-ended video understanding, yet they remain prone to fluent responses unsupported by video evidence. Existing training-free methods typically apply a globally fixed visual intervention or construct a contrastive branch through input perturbation. The former cannot accommodate video-dependent fusion paths, while the latter can be compensated by cross-frame redundancy. We therefore propose Video-Adaptive Debiasing via Evidence Reweighting (VADER), a training-free framework with two complementary modules. Visual Focus Reallocation (VFR) automatically instantiates an intervention policy for each video-question input: it diagnoses layer-wise visual-to-text evidence flow, determines where to intervene, and derives how strongly to reallocate pre-softmax attention from system-token to video-token blocks. Selective Evidence Erasure (SEE) independently masks high-importance visual tokens in every frame, constructing a prior-biased branch that is difficult to compensate through neighboring frames. Contrastive decoding then down-weights predictions that remain confident after selective evidence erasure. Across multiple VideoLLMs, VADER yields substantial improvements on event-level grounding and temporal consistency; on LLaVA-Video-7B, it reaches 72.60% accuracy on EventHallusion.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08622
PDF
-
Wiener Representation Filtering for VLM Hallucination Suppression
2026-08-08 14:51:17Ameen Ali, Tamim Zoabi, Lidor Brami, Lior WolfAbstract
Vision-language models (VLMs) excel at open-ended captioning and visual QA but often describe objects, attributes, or relations absent from the image, a phenomenon known as object hallucination. We propose a {training-free, post-hoc representation editing technique} that operates in the representation space of the language backbone. The method performs a lightweight, one-time offline calibration on a modest paired dataset to estimate the required covariance structures, using only forward passes and empirical second-order statistics with no gradient updates or fine-tuning, after which the correction is absorbed directly into the model's existing weights. By modeling hidden states as a superposition of truthful and hallucination-associated components, we derive a Wiener-type estimator whose optimal gains are given in closed form from the covariances of paired truthful and hallucinated representations. An eigendecomposition yields mode-wise attenuation that respects a stability criterion, i.e., the filter responds continuously to estimation noise. The correction is applied once to the feed-forward output projections of selected deeper layers, at inference time, the model runs unchanged and at the same speed. Experiments on LLaVA-1.5, MiniGPT-4, Gemma3, and mPLUG-Owl2 demonstrate consistent reductions in object hallucination on CHAIR, POPE, and MME while maintaining caption fluency and overall response quality. We further demonstrate the generality of our approach on the TempCompass video understanding benchmark and on discrete diffusion language models for grounded dialogue, showing that representation filtering reduces hallucinations even in temporal video reasoning and multi-step, sequence-wide denoising settings.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08167
PDF
-
SurgWMBench: A Vision-Based Benchmark for World-Modeling Surgical Instrument Motion Planning
2026-08-08 11:30:50Huanrong Liu, Weiliang Huang, Bob Zhang, Weichao Cai, Chunlin Tian, Qingbiao LiAbstract
Reliable surgical planning requires models that move beyond recognizing the current surgical step or imitating expert demonstrations, and instead anticipate how instrument motion reshapes subsequent operative states. Most surgical video understanding methods focus on recognizing phases, actions, or workflow states, while providing limited support for explicitly modeling instrument motion. Conversely, existing tool motion prediction methods can forecast instrument trajectories, but they generally do not capture the coupled evolution of future surgical video states. World models offer a natural framework for jointly modeling visual state transitions and instrument motion dynamics. However, existing surgical world model studies remain largely centered on visual generation quality, relying on generation-oriented metrics such as FVD and CD-FVD. These metrics are poorly aligned with instrument motion planning, as they do not directly measure whether predicted trajectories are geometrically accurate, temporally coherent, or actionable for downstream planning. This limitation is partly structural, since the field lacks public datasets and standardized evaluation protocols that provide the benchmarking infrastructure needed to assess motion-centric capabilities in surgical world models. In this paper, we introduce SurgWMBench, a vision-based benchmark for short-horizon surgical motion planning and dynamics prediction. Given intraoperative image sequences and historical instrument trajectory, SurgWMBench evaluates both near-future instrument motion prediction and stability under continuous rollout or input perturbations.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08070
PDF
-
SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning
2026-08-08 06:48:08Keyang Zhong, Kuo Wang, Peng Liu, Quanlong Zheng, Junlin Xie, Zhijia Liang, Yanhao Zhang, Guanbin LiAbstract
Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multimodal models with limited context and the grounding of key video segments. While Chain-of-Tool-Thought (CoTT) agent systems enable iterative retrieval and inspection, they suffer from error propagation due to rigid zoom-in strategies that lack recovery mechanisms. In this work, we address these challenges through SCOUT (Self-Checking Chain-Of-Tool-thought), a recovery-aware agentic framework introducing an adaptive policy that evaluates intermediate tool observations and dynamically trades off exploitation (zoom-in) and exploration (region switching), enabling robust multi-hop reasoning over extremely long horizons. However, training such multi-turn tool-using agents remains challenging, as existing RL methods rely on sparse outcome-level rewards and lack supervision over extended decision trajectories, resulting in suboptimal credit assignment for long-horizon reasoning. To address this, we develop UPS-GRPO, an uncertainty-prioritized policy optimization method that concentrates exploration on high-uncertainty post-tool states while preserving sample efficiency. We further introduce a turn-level advantage decomposition that integrates outcome rewards with tool-grounded temporal alignment rewards for improved credit assignment. Experiments show that SCOUT achieves state-of-the-art results on ultra-long egocentric benchmarks, while remaining competitive on shorter-horizon long-video settings.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07959
PDF
-
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
2026-08-07 18:00:02Yeeun Choi, Youngbeom Yoo, Joon-Young Lee, Hyolim Kang, Seon Joo KimAbstract
When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs). This ultra-long setting necessitates a two-stage paradigm: query-agnostic memory construction followed by retrieval-based inference. Prior work invests in complex memory construction to pre-model high-level relations in videos, despite not knowing the downstream query at build time. We instead prioritize high-recall retrievability during memory building, and defer query-specific, high-level relation composition to inference time. To this end, we propose MERIT(Multi-key Episodic Retrieval with Inference-time Temporal expansion), a simple yet effective agentic framework for ultra-long video understanding. First, we formulate an episodic multi-key representation that enables precise retrieval of fine-grained memories through a simple key-matching mechanism. Second, we introduce a neighbor filtering mechanism to capture broader semantic context without the massive computational overhead of global memory construction. This is achieved by expanding the temporal scope exclusively around the retrieved segments at inference time. By leveraging simple key-matching with this on-demand temporal expansion, MERIT achieves state-of-the-art performance across three long-video benchmarks: EgoLifeQA, LVBench, and Video-MME (Long).
Abstract (translated)
URL
https://arxiv.org/abs/2608.07663
PDF
-
Training-Free Speech-Centric Omni Understanding with Frozen VLMs
2026-08-07 17:59:51Ankan Deria, Hanoona Rasheed, Xilin He, Fahad Shahbaz Khan, Salman KhanAbstract
Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically introduce dedicated audio encoders and rely on expensive audio-video-text training, tightly coupling omni capability to specific VLM backbones and potentially weakening their existing visual and reasoning abilities. This raises three questions: whether native omni training is necessary for every new VLM, whether speech-centric omni capability can be added while preserving the original backbone, and where richer acoustic representations remain essential. We introduce Training-Free Omni (TFO), a plug-and-play framework that converts a frozen VLM into a speech-centric omni model without architectural modification, or multimodal re-alignment. TFO uses Whisper to extract confidence-filtered, timestamped transcripts and routes them through the VLM's existing language interface, while leaving its visual pathway unchanged. Across matched comparisons with native omni models on 56 benchmarks and 21 languages, TFO is competitive on audio-visual understanding, improves average audio-only performance across all five model settings, and achieves substantial multilingual speech gains. Freezing the VLM also generally preserves stronger image/video understanding, visual grounding, coding, mathematical reasoning, and medical question answering than the corresponding native omni checkpoints. These results show that strong speech-centric omni understanding can often be obtained through modular audio-to-language routing rather than costly backbone-specific training.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04242
PDF
-
AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward
2026-08-07 08:03:51Mingyang Wu, Kaituo Feng, Bohao Li, Kaixiong Gong, Zihao Yin, Xiangyu YueAbstract
Detailed audio-video joint captioning is essential for multimodal video understanding and generation. However, prior works are constrained by three main limitations: (1) the scarcity of high-quality public datasets with fine-grained audio-visual joint captions; (2) reinforcement-learning methods that rely on coarse reward signals; and (3) the lack of a benchmark and metric for evaluating detailed audiovisual captions at the atomic level. To address these challenges, we propose: (1) AVCap-100K, a high-quality dataset of 100K temporally aligned, detail-rich audio-video captions; (2) AVCap, a model optimized via Detail-Aware GRPO (Da-GRPO) that achieves state-of-the-art performance among open-source models and matches or surpasses proprietary models on several evaluations; and (3) AVCap-Bench and AVCap-Score, a specialized benchmark and metric for evaluating atomic-level details in audiovisual captions. Our code, models, and datasets are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.06930
PDF
-
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
