Video_Caption
-
LazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension
2026-09-29 12:53:57Arka Mukherjee, Kaleen Shrestha, Larissa Zhu, Maja Matari\'cAbstract
Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture. However, most methods focus on coarse captioning of extracted image frames that are computationally inefficient and require models with large context windows. While past work has explored efficient methods through multimodal retrieval-augmented generation (RAG), they rely on lossy embeddings that lose temporal context and fine-grained detail. Few works to date have investigated how VLM-based query-relevant information retrieval can be optimized. We introduce LazySloth, an efficient tree-based search method that speeds up video comprehension and retrieval tasks 2.9-8.3x (compared to existing agentic methods) through bounded captioning of portions of the video considered irrelevant by a VLM of the video. Compared to contemporary specialized video-understanding VLMs and RAG-based methods, LazySloth achieved similar or better final task accuracy across two recent open-source base VLMs--Gemma 4 31B and Qwen3.6 27B--across four benchmarks. LazySloth reduced the gap between the base open-source model and a closed-source model, GPT-4o. Ablations showed that replacing VLM scene understanding with CLIP-based retrieval cost 8.8-19.9% in accuracy, while lazy tree construction matches eager construction at a fraction of the captioning cost. With LazySloth, we demonstrate the possibility of faster long-video comprehension without substantial loss in performance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37426
PDF
-
When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs
2026-09-29 12:13:56Xiang Hu, Jiazuo Yu, Lu Zhang, Yunzhi Zhuge, Huchuan LuAbstract
Streaming video understanding requires Video Large Language Models (Video-LLMs) to reason over continuous visual streams under causal constraints. As the visual history grows, a bounded visual?processing budget requires evidence selection that balances temporal recency with query relevance. Recent-only selection excludes potentially relevant historical evidence, whereas Semantic-only retrieval can displace useful recent context when relevance scores are ambiguous. We introduce WRWS (When to Retrieve, When to Stay), a training-free framework for uncertainty-adaptive evidence allocation. A lightweight external vision-language encoder scores query relevance across the observed history, while an adaptive allocation module uses the normalized entropy of the similarity distribution as a proxy for retrieval uncertainty. WRWS favors semantic retrieval when relevance cues are reliable and strengthens the recency prior under uncertainty. Following a retrieve-first, encode-later pipeline, WRWS selects evidence before target-model visual encoding, such that only the selected observations are processed by the costly target Video-LLM. Experiments across four Video-LLM families and multiple model scales demonstrate competitive accuracy on StreamingBench and OVO-Bench. In our efficiency evaluation, WRWS reduces average vision-to-answer time to 47.93% of the state-of-the-art method. Code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37345
PDF
-
GleanVID: Complementary Token Selection for Efficient Video Large Language Models
2026-09-29 08:50:57Shuo Yang, Changbai Li, Rui Tang, Xinyu Zhao, Linlin Yang, Baochang ZhangAbstract
Video Large Language Models (VideoLLMs) have achieved strong video understanding capabilities but incur substantial inference overhead due to the large number of visual tokens. Existing VideoLLM token compression methods largely rely on selection-independent scoring, overlooking cross-frame complementarity and consequently retaining redundant evidence across frames. Instead, we view video token selection as a progressive evidence accumulation process. It aims to retain visual evidence that is individually informative and collectively complementary under a limited token budget. Building on this insight, we introduce GleanVID, a training-free inference acceleration framework for VideoLLMs. Specifically, GleanVID first allocates the global token budget across frames according to temporal novelty and then selects tokens by jointly considering local representativeness and subspace complementarity, thereby preserving richer and less redundant visual evidence. Extensive experiments across diverse VideoLLMs and benchmarks demonstrate that GleanVID consistently achieves state-of-the-art performance. Notably, with only 25% of visual tokens, GleanVID preserves 98.6% of Qwen3-VL's original performance while reducing its prefill latency by 44.7%. On LLaVA-OV-7B, GleanVID at a 25% retention ratio even slightly surpasses the original model.
Abstract (translated)
URL
https://arxiv.org/abs/2609.37042
PDF
-
Counterfactual Attention Policy Distillation for Temporal Video Grounding
2026-09-29 08:12:10Shaobo Ju, Haiyang Yu, Xuecheng Wu, Qiong Wu, Jiacong Wang, Fan Shi, Jun Peng, Yiyi ZhouAbstract
Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, which is however often limited by repeated actions and visually similar contexts in long videos. In this paper, we study this issue from the perspective of On-policy distillation (OPD) and propose a new training regime for MLLMs termed Counterfactual Attention Policy Distillation (CAPD). In particular, OPD is a viable solution for MLLMs via providing dense teacher supervision on student-generated trajectories. But its next-token based teacher-student distillation is hard to identify the specific video segments supporting each predicted timestamp, which is critical for temporal grounding. In this case, CAPD measures how masking each temporal group changes the teacher's output distribution. The resulting counterfactual influence calibrates the teacher's attention and weights token-level distillation, allowing the student to learn the temporal evidence that affects boundary prediction. To validate CAPD, we trained it on Qwen3-VL-8B-Instruct using only 2,500 samples for one epoch, and evaluated it on the TimeLens and multiple general video benchmarks. Experimental results show that CAPD improves average recall by 12.0% relative to GRPO on TimeLens while preserving general video understanding, achieving comparable accuracy to the base model.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34581
PDF
-
EGSD: Event-Grounded Self-Distillation for Streaming Video Understanding
2026-09-29 06:15:16Yuwei Miao, Xuesheng Zhang, Wenhao Zou, Jixia Zhang, Jianwei Lv, Bo Yuan, Junfeng Wang, Shiao XieAbstract
Real-time video understanding requires incrementally maintaining a memory of streaming content, and optimizing this requires dense process signals. On-Policy Self-Distillation (OPSD), which lets one model serve as both teacher and student with the teacher receiving additional privileged information such as the question and ground-truth (GT) answer, can supply such token-level signals. However, applying it directly to streaming video raises two problems. (1) The student cannot be optimized end-to-end, where memory is written before the question arrives, yet the teacher scores it with the question-and-GT privilege, misaligning their preferences. (2) Effective-entity memory collapses, where the question-and-GT privilege makes the teacher favor only question-relevant entities, and token-mean averaging over a memory renders its signal invariant to how many entities that memory covers, both driving memory against the streaming need for diversity. To address these issues, we propose Event-Grounded Self-Distillation (EGSD), which characterizes streaming memory as an incremental update over verifiable Events (key visual entities, actions, and details) and targets the two problems on this basis. For problem (1), we adapt the OPSD signal into a multiplicative weight combined with the outcome reward; for problem (2), we re-weight the teacher with Events as privileged information to counter its question-relevance bias, and add an entity-coverage reward to supply the coverage preference the token-mean teacher lacks. Extensive experiments on mainstream online and offline benchmarks show EGSD achieves strong performance, reaching 79.8% on StreamingBench and 73.4% on the OVO-Bench Real-Time track, while memory analysis shows effective-entity recall rises 17.4% at only 6.8% more memory length.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36803
PDF
-
Causal-EVC: Breaking Emotional Spurious Causality via Spatiotemporal Grounding and Counterfactual Intervention
2026-09-29 05:49:15Cheng Ye, Weidong Chen, Peipei Song, Zhendong MaoAbstract
Emotional Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the importance of visual causes to guide emotion perception and caption generation, they fundamentally rely on simple attention matching, which inevitably suffers from {causal redundancy and spurious correlations} in co-occurrence bias (e.g., misclassifying ``sadness'' as ``joy'' on a sunny beach), leading to severe shortcut learning from confusing backgrounds. Furthermore, existing evaluations fail to verify whether models have genuinely mastered causal reasoning or merely exploited background confounders. To address these limitations, we first construct {EVC-CauseGround}, a comprehensive benchmark with dense spatio-temporal causal annotations. Crucially, it introduces a carefully selected {Causal-Faithfulness Subset} to explicitly quantify genuine emotion-cause attribution. Second, we propose {Causal-EVC}, an emotion-grounding captioning framework, which introduces a Motion-guided Causal Spatiotemporal Localization module to precisely decouple causal triggers from background confounders. Besides, we introduce an Interpretable Sparse Emotion Routing module. By synthesizing counterfactual representations and formulating a novel counterfactual contrastive objective, we enforce the model to anchor its emotion predictions strictly on authentic causal triggers instead of confusing background. Extensive experiments show that Causal-EVC not only achieves the best performance on semantic metrics but also exhibits significant advantages in the causal-faithfulness subset, which demonstrates that our model could mine emotional cues from genuine visual causes and mitigate co-occurrence bias for interpretable multimodal emotion understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36776
PDF
-
Beyond Binary Preferences: Graded Preference Optimization for Limb-Motion Captioning
2026-09-29 03:37:06Yanan Wang, Tingsong Li, Kaixun Jiang, Chongyang Zhong, Chenwei Xoe, Zhaohe LiaoAbstract
Vision-Language Models (VLMs) can generate rich video captions, yet often misidentify which person performs an action or which limb is involved, particularly across camera cuts. Improving these details requires evaluation and training that distinguish missing information from incorrect assertions. We introduce FlexBench, a benchmark spanning 3,105 shots and 18,161 evaluation queries, with human-verified identities and systematic per-person coverage of fine-grained limb actions and states. Its reference-derived checklists support automated assessment of complete captions in their person and shot contexts. Our Graded Physical Alignment score (GPA) awards credit for correct content and deducts points for incorrect or fabricated actions, making these errors explicit in the aggregate score. Building on this rubric, we propose Graded Margin Direct Preference Optimization (GM-DPO), which assigns stronger preference margins and greater training weight to more severe action errors. Across three VLM backbones, GM-DPO achieves the highest substantive-action and GPA scores among the evaluated preference objectives, improving GPA over DPO by 2.02-3.40 points. On Qwen3-8B, it reduces the weighted hallucination rate by 21.3% relative to DPO. These gains accompany sustained long-form output, improved shot structure, and competitive performance on three additional multimodal benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36628
PDF
-
MemEvo: Automatic Discovery of Streaming Video Memory Mechanisms
2026-09-29 02:59:42Guohong Liu, Jialei Ye, Shanhui Zhao, Yunxin Liu, Yuanchun LiAbstract
Query-agnostic streaming video understanding requires vision-language models to continuously compress an indefinitely growing visual stream into a bounded memory before future queries are known. The performance depends critically on the memory mechanism--what observations to preserve, how to represent and consolidate them, and what information to retrieve when a query eventually arrives. Rather than designing a single memory architecture by hand, we formulate memory design as a search problem over executable memory programs. We introduce a lightweight domain-specific language that expresses memory mechanisms through structured primitives for representation, admission, retention, consolidation, budgeting, and retrieval, while enforcing causal and bounded-memory constraints. Although structured, the derived program space remains large and contains heterogeneous, conditionally dependent design choices whose effects can only be assessed via downstream execution. We therefore propose MemEvo, an LLM-driven auto-research framework that uses pretrained LLM as a semantics-aware proposal model to iteratively generate and refine candidate memory programs based on accumulated experimental feedback. At runtime, a deterministic evaluation pipeline validates and evaluates each candidate, while the underlying vision-language model remains frozen throughout discovery. We finally produce a training-free, bounded-memory mechanism. Extensive experiments on StreamingBench and OVO-Bench demonstrate strong streaming video understanding performance together with substantial context and inference efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.36581
PDF
-
Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding
2026-09-25 11:19:16Xiao Zhang, Wang Zeng, Sheng Jin, Wentao Liu, Chen Qian, Shichao KanAbstract
Large vision-language models (LVLMs) have recently achieved remarkable progress in general-purpose video understanding. However, their application to real-world surveillance remains challenging due to the lack of large-scale domain-specific datasets and the limitation of passive observation from fixed viewpoints. In surveillance scenarios, critical visual evidence can be easily missed when targets are distant, small, occluded, or move beyond the current camera view. In this work, we introduce CamVLM, a new framework for Thinking with Cameras, which enables LVLMs to actively acquire visual evidence in real-world surveillance by continuously controlling camera viewpoints. We first construct CCTV-Anomaly, a large-scale surveillance video understanding dataset containing 14,133 videos across 10 anomaly categories, with detailed captions and event annotations. We further formulate viewpoint control as an active visual perception problem and build CamTrack-53K, an object-centric viewpoint trajectory dataset for learning camera actions. Moreover, we propose a reinforcement learning based viewpoint policy optimization framework, which models camera control as a sequential decision-making process and learns long-horizon observation strategies beyond supervised trajectory imitation. Extensive experiments demonstrate that CamVLM achieves state-of-the-art performance under both passive observation and dynamic viewpoint settings, validating the effectiveness of active camera-based reasoning for surveillance video understanding. Our datasets, model, and code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.06475
PDF
-
MVVBench: Benchmarking 4D Reasoning in Vision-Language Models
2026-09-25 08:02:42Hyungjin Chung, Byeongjun Park, Joonseok Lee, Hojun Kim, Jaeho Choi, Byung-Hoon KimAbstract
Multi-view video understanding requires integrating spatial and temporal evidence across multiple, often non-overlapping camera streams: tracking entities as they transition between viewpoints, aligning events across time, and reasoning about latent 4D continuity rather than any single visible frame. We introduce MVVBench, a benchmark for multi-view video reasoning built from real world multi camera datasets. Questions are curated to be monocular-ambiguous along both the view and the temporal axis: each question is unanswerable from any single view in the designated input set, and the majority are further unanswerable from any single moment. Each question becomes uniquely solvable only by jointly reasoning across views and across time. MVVBench spans diverse dynamic scenes and probes six capabilities: implicit/explicit attribute identification, implicit/explicit relative distance, relative camera pose, and compositional counting, with human-authored QA and rigorous verification. Beyond benchmarking, we provide an extensive analysis of when and why current vision language models succeed or fail, characterizing errors due to temporal mis-localization, cross-view identity breaks, and brittle multi-hop reasoning. We then study inference-time elicitation strategies that unlock latent multi-view competence---task-specific chain-of-thought scaffolds and structured cross-view evidence aggregation---yielding substantial gains without retraining. Finally, we present preliminary evidence that reinforcement learning with verifiable rewards can elicit some latent multi-view competence in the base model, pointing to training-time approaches as a promising direction for future work. Together, MVVBench offers a rigorous evaluation of 4D multi-view reasoning and a foundation for future progress toward reliable embodied perception.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30952
PDF
-
TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
2026-09-25 01:21:25Yibo Ma, Qianqian Zhang, Peng Liu, Tiancheng ZhaoAbstract
Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history is maintained, or how responses are triggered. As a result, similar scores may correspond to different workloads, failure modes, and operational behavior. We introduce TRACE (Temporal Audit and Condition-aware Evaluation), a condition-aware benchmark and evaluation framework that makes these factors explicit. TRACE combines temporally audited visual tasks with evidence timing and instruction-dependent trigger annotations, a unified causal Core--Adapter protocol that controls information availability while recording actual history processing and response events, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. On 1,240 records from 517 videos, we evaluate eight publicly available models or systems in eight configurations. We find that nearly identical QA accuracy can mask substantial differences in completion, answer validity, and generation workload, while proactive performance separates into response quality, response delay, false alarms (responses emitted while no target window is currently valid and a later one remains), and missed target windows. These results show that streaming-video performance should be interpreted as execution-conditioned system behavior rather than a single score. Our benchmark and code can be accessed at \href{this https URL}{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30670
PDF
-
Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models
2026-09-24 04:02:18Shuzhi Gong, Fengze Sun, Yuansan LiuAbstract
Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these stages are typically evaluated on different benchmarks and distributions, making it difficult to determine where hallucinations originate. We first organize existing benchmarks around these stages and show that their scores provide inconsistent diagnostic signals: stronger stage-level performance does not reliably imply lower downstream hallucination, and even benchmarks targeting the same capability can disagree. We therefore introduce a causal stage-intervention protocol that overwrites individual stages while holding the downstream task fixed. Across 60,008 runs on three video-agent architectures, we find that grounding is the dominant source of downstream error, with roughly four times the causal impact of corrupting visual observations. Successful grounding depends primarily on locating the correct region rather than precise temporal overlap, explaining why standard mIoU metrics poorly predict downstream reliability. We further find that incorrect evidence is substantially more harmful than missing evidence. Finally, auditing existing benchmarks against these interventions reveals that their scores do not reliably predict causal cascade sensitivity and can fail under distribution shift. These results motivate intervention-based, stage-aware evaluation for trustworthy video agents.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28991
PDF
-
CinematicVQA: Benchmarking Film-Grammar Reasoning in Large Vision-Language Models
2026-09-23 21:47:34Shuo Xing, Pooja Verlani, Balu Adsumilli, Zhengzhong TuAbstract
Cinematography, the craft of visual storytelling through framing, lighting, and camera operation, fundamentally shapes how audiences perceive and emotionally engage with video content. While Large Vision Language Models (LVLMs) have made remarkable progress in video question answering, existing benchmarks primarily focus on identifying low-level techniques rather than understanding their storytelling impact. To address this, we introduce CinematicVQA, the first-of-its-kind benchmark for cinematic video understanding that goes beyond technique recognition to evaluate film-grammar reasoning, utilizing our introduced Cinematic Scene Graph (CSG), a structured representation that links filming techniques to their perceptual effects and narrative functions. Through comprehensive evaluation of state-of-the-art LVLMs, we reveal a striking semantic gap: models consistently perform higher on describing visual presentations than on identifying the underlying techniques. Surprisingly, Chain-of-Thought prompting fails to provide consistent gains and degrades performance for most models, suggesting that current LVLMs lack sufficient cinematic domain knowledge to benefit from step-by-step reasoning. Fine-tuning on \textsc{CinematicVQA-train} yields consistent improvements, particularly for narrative function and multi-hop reasoning. Overall, \textsc{CinematicVQA} serves both as a rigorous benchmark for cinematic evaluation in LVLMs and as a practical dataset for training more film-aware video models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28813
PDF
-
Prompt, Probe, Train, or Annotate? Single-camera sports video understanding in amateur settings
2026-09-23 13:05:24Sai Varun Kodathala, Prashanth Pollishetty, Jaylen CargillAbstract
Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Amateur team sport is a useful, largely untested place to check that assumption: over eight million students played a school sport in the United States in 2024-25 alone, almost none of it filmed by more than a single fixed camera, with several candidate actors crowded into frame and no operator or second angle to fall back on. Using volleyball as a test case, we ask whether strong performance on general video and world-model benchmarks translates into reliable, per-player attribution once footage is this chaotic, turning footage into statistics through a chain of tasks from finding play boundaries to naming who did what. We evaluate four approaches (prompting and agentic reasoning over frontier vision-language models, classical computer vision with small trained specialists, self-supervised video world models, and manual annotation) at every stage, on 66 amateur matches with 46,648 human-labelled contacts, filmed under conditions no published benchmark uses. No single paradigm wins every stage, and static, single-frame computer vision is not competitive at any stage involving motion or identity. A prompted model segments matches well, yet a far smaller trained model beats it at spotting contacts for a fraction of the cost, and the sport's own rules recover rally outcomes the pixels cannot. Identity is where every automated approach struggles: a jersey number is a static fact temporal reasoning cannot recover if never visible, unlike sporting action, a repeated motor pattern a temporal model can exploit, which is why holistic reasoning improves event detection while identity stays unchanged. We close with where each approach earns its cost, and what transfers beyond volleyball to amateur sport.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28049
PDF
-
A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery
2026-09-22 22:58:46Ana Manzano Rodr\'iguez, Pascal Mettes, Marlies P. Schijven, Cees G. M. SnoekAbstract
Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize them are evaluated with flat per-level metrics that ignore cross-level coherence and error structure. In this paper we make two contributions to address this problem, (i) we introduce SurgHiBench, the first hierarchy-aware evaluation suite for surgical video understanding, with three tasks measuring recognition, consistency, and severity across granularity levels. We evaluate a general-purpose CLIP model, a Euclidean surgical model, and, as second contribution: (ii) HyperSurg, a new hyperbolic model that enforces phase-step containment via entailment cones, across four (existing) datasets spanning three procedure types. The suite reveals that two models with the same accuracy can produce predictions of very different error severity, ranging from sibling confusions within the correct phase to unrelated cross-phase predictions. Hyperbolic geometry shifts predictions toward the correct procedural neighborhood, and these gains scale with the tree-likeness of each dataset's annotation hierarchy, providing a principled indicator when hierarchy-aware geometry helps.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27139
PDF
-
Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models
2026-09-22 07:08:13Trung Nguyen Quang, Yuhao Dong, Shuo Sun, Shuai Liu, Shulin Tian, Kim-Hui Yap, Ziwei LiuAbstract
HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that compound across steps, while most data used for reinforcement learning with verifiable rewards (RLVR) rarely demands a chain of visual evidence, so these weaknesses are likely to stay unexposed. We observe the same problem in video, where this framework has not yet been explored. We therefore build Video-HopChain, a dataset of 22,550 multi-hop video questions over 13,378 videos, together with a held-out benchmark of 1,000 questions. Each question chains three to six yes/no questions about moments in one video, and each yields one of two integers depending on its answer. The final answer is the sum of these integers, so an exact match on that sum gives the verifiable reward that RLVR needs. We first train Qwen3-VL-8B with GRPO on a standard video dataset, and a second stage on Video-HopChain then raises the mean over eight video understanding and reasoning benchmarks from 55.4 to 57.9 and improves every one of them. Training on such a dataset, however, exposes a known limitation of GRPO: its learning signal comes from the reward variance within a group, so hard questions whose rollouts are all incorrect and easy questions whose rollouts are all correct both leave the group with no gradient. To recover these groups at the same compute budget, we introduce Confidence-Gated Exploration (CGE). With 8 rollouts per question, CGE samples the first 4 as usual. If these 4 are either all correct or all incorrect, it samples the last 4 with the policy's most confident token masked inside the reasoning span, and removes the masked positions from the loss while all 8 rollouts enter the advantage. With CGE, the mean rises further to 59.3. We release the dataset, the checkpoint, and the data generation and training code.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25773
PDF
-
PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding
2026-09-20 12:41:39Siru Zhong, Qiongyan Wang, Xiaohui Lv, Yuzheng Zhuang, Shuai Tao, Wulong Liu, Haohuan Fu, Yuxuan LiangAbstract
Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens, or alter internal key-value (KV) caches. We introduce Prefix-Steered Recurrent Memory (PREM), a memory-token-free framework for frozen vision-language models (VLMs). PREM separates video ingestion from query answering: a recurrent writer distills visual streams into a compact 256 KiB multi-slot associative state, while a question-conditioned readout adds memory-derived key/value (K/V) steering modulations to existing non-visual prompt prefixes during prefill. This enables write-once, query-many inference without extra prompt tokens or decoding recurrence. Across six long-video benchmarks in offline and streaming end-of-stream settings, PREM consistently outperforms frozen baselines at every evaluated visual budget. Under a constrained budget of 16 frames, PREM improves macro-average accuracy by 3.06% on Qwen2.5-VL-3B, with gains of 11.0% on action antonym identification and 9.9% on localized needle retrieval. These gains require tuning 0.24% of backbone parameters at 0.03 GiB of peak GPU memory overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23601
PDF
-
GPEC: Efficient Pre-LLM Gaussian Process Embedding Correction for Cardiac Video Caption Generation
2026-09-18 19:52:05Arefeh RezaeiAbstract
Multimodal large language models (MLLMs) have shown strong potential for video understanding and caption generation, but their performance may decline in specialized medical imaging domains such as echocardiography. This work introduces Gaussian Process Embedding Correction (GPEC), a modular and computationally efficient pre-LLM error-correction method that improves the visual representations used by VideoChat2 for cardiac ultrasound caption generation. GPEC is inserted between the visual projection layer and the language model and learns a residual correction that moves the projected visual representation toward an annotation-guided target. The target is constructed by converting structured video annotations into qualitative attributes, generating a fixed-format reference caption, and mapping it into the language-model embedding space. The correction is modeled using a sparse variational Gaussian Process with inducing points, natural-parameter variational updates, and a block-wise linear kernel, while the original VideoChat2 components remain this http URL method is evaluated using representation-level, caption-level, content-oriented, and execution-time metrics by comparing the original VideoChat2 with VideoChat2 + GPEC under identical input and reference conditions. Results show improved caption similarity and content alignment after applying the proposed correction. Furthermore, GPEC adds less than 0.05 s of inference-time overhead per video in the evaluated setting. These findings indicate that GPEC can improve caption generation in specialized medical video domains with minimal computational cost, without requiring end-to-end fine-tuning of the pretrained multimodal backbone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00196
PDF
-
VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration
2026-09-18 09:09:34Changbeen Kim, Junwon Chang, Kipyo Kim, Risa Shinoda, Kuniaki Saito, Donghyun KimAbstract
While Video Large Language Models (Video-LLMs) have recently demonstrated strong performance, reliably evaluating their fine-grained video understanding remains challenging. Existing benchmarks often rely on question answering or ground-truth caption matching, where models may succeed through superficial cues and incomplete annotations. To this end, we introduce VidOmni-Bench, a benchmark that requires models to verify whether each event in dense video captions is supported by the video. VidOmni-Bench consists of 500 videos spanning five complexity types and diverse durations from 4 seconds to 90 minutes. After collecting videos along these axes, we use diverse Video-LLMs to generate dense captions and obtain human-verified sentence-level labels, where sentences containing incorrect events serve as hard negatives for evaluation. Our experiments on VidOmni-Bench reveal three key findings: (i) Video-LLMs frequently generate hallucinated descriptions in dense video captioning; (ii) they also struggle as verifiers, failing to reliably detect plausible but incorrect event descriptions; and (iii) model weaknesses vary across video complexity and duration, revealing diverse, model-specific bottlenecks in current Video-LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21521
PDF
-
AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents
2026-09-18 06:56:33Seoyeon An, Hyeonseo Jang, Minsu Kim, Chanho Lee, Younghan Park, Kangwook LeeAbstract
Comprehensive video understanding is crucial for advancing artificial intelligence toward the intricate dynamics of the physical world. While recent advances in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in video understanding, existing benchmarks remain confined to simple scene-level queries or global summaries that require only single-step inference. Real-world video understanding involves more challenging tasks that require multi-hop multimodal reasoning, and there is a critical absence of video benchmarks equipped to rigorously evaluate these agentic capabilities. To bridge this gap, we introduce AgentVidBench, a multi-hop video question answering benchmark focused on evaluating the spatial, temporal, and causal reasoning capabilities of MLLM agents. Beyond standard question-answer pairs, AgentVidBench provides step-by-step solution traces to support trajectory evaluation that assesses whether agents explicitly acquire the evidence needed to justify their answers. Experiments with 12 proprietary and open-source MLLMs show that single-turn performance remains limited on AgentVidBench, while integrating these models into state-of-the-art agentic workflows generally improves performance with respect to both accuracy and trajectory scores. We further present a simple yet effective agentic strategy that serves as a competitive baseline on AgentVidBench, establishing our benchmark as a holistic testbed for future research on agentic video understanding. Code and datasets are available at this https URL and this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21386
PDF
