Video-Language Model Evaluation

Ask about this topic

Overview

The field develops tests and metrics for whether models can answer questions, describe events, localize evidence, and follow instructions in videos, including long, streaming, and audio-visual settings. Common approaches include human-annotated benchmarks, controlled tests that shuffle frames or alter evidence, and measures of temporal grounding, hallucination, efficiency, and response timing. Results often show that strong question-answering scores can coexist with weak event ordering, evidence localization, and resistance to misleading cues. A central challenge is separating genuine use of video evidence from shortcuts, while making results comparable across models and realistic about deployment constraints.

Latest papers

CardsList

103 papers20 papers in the last four weeks, down 5% on the four weeks before. 0.1% of all new papers.

Aug 3, 2026

RSVideo: Are Your Vision-Language Models Ready for Remote Sensing Videos?

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 backbones. Codes will be available at https://github.com/HongjieZhou0329/RSVideo.

Hongjie Zhou, Shiqin Wang, Haoyang Chen +5

Wuhan University · Zhongguancun Academy

Video-Language Model EvaluationRemote SensingRL for VLMsRemote Sensing VLMs
AskPDF
Jul 14, 2026

Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks

Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding. We audit this assumption across twenty models spanning 2-78B parameters and ten architecture families. We introduce the Visual Dependency Gap (VDG), the difference in per-question correctness between original-video and black-screen conditions. Paired McNemar tests on MVBench show that accuracy and visual dependency are separable: models differ on original video (p = 0.0003) but not on black screens (p = 0.53). Across models, task-type rankings are stable: Attribute Perception is strongly visual, whereas Temporal Reasoning approaches the language-only baseline. A diagnostic ladder from black screen to single frame, shuffled frames, and original video reveals that frame diversity supplies most of the visual benefit, while temporal order contributes near-zero accuracy across sixteen open-weight models. An ablation from 0.5 to 24 FPS rules out sparse sampling as the cause. H.264 experiments further show that stable aggregate accuracy conceals bidirectional question-level answer flips. The diagnostic also generalizes to four API-accessed models, whose VDG values range from 0.025 to 0.315. These results motivate VDG as a standard audit for whether video benchmarks measure visually grounded capability. Code is available at https://github.com/JaeLee18/accuracy-without-grounding.

Jae Joong Lee

Department of Computer Science Purdue University West Lafayette, Indiana, USA

VLM EvaluationVideo-Language Model EvaluationVideo-Language ModelsTemporal Video Understanding
AskPDF
Jul 13, 2026

Do Video-LLMs Actually Watch? Diagnosing Character-Tracking Failures in Long-Form Video

Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score this kind of task, and the strongest open-source 7--8B models now reach 37--38% on InfiniBench's global appearance task, which asks exactly that. But does that score come from tracking the named character, or from something easier? We test this with a nine-condition diagnostic protocol applied to three architecturally distinct open-source Video-LLMs, with Gemini2.5Flash as a frontier reference, and find the accuracy does not come from character tracking. When we change the character named in the question to a different cast member, leaving the video and answer options untouched, the models change their answer only 4--31% of the time, so they are largely ignoring who the question asks about. Breaking that test down by the gender of the swapped name shows why: the models react more when the name is changed to a different-gender character than to a same-gender one (a 13--28 point gap), picking up coarse gender cues but unable to tell same-gender individuals apart. This shallow processing surfaces again when we drop the multiple-choice options and ask the same questions open-endedly: open-source accuracy drops 18--25 points, with none of 151 answers fully correct, versus a 12-point drop for Gemini. Further checks rule out the obvious innocent explanations, adding subtitles, using the most informative frames, or doubling the number of frames all leave character tracking unimproved, so the bottleneck is not how much video the model sees but how it ties that video to the person the question names. We release a diagnostic toolkit for auditing what such benchmark scores actually measure.

Mohammad Al-Ratrout, Shayla Sharmin, Aditya Raikwar +1

Visual Object TrackingVideo-Language Model EvaluationVideo QALong-Video UnderstandingShortcut LearningMultimodal Model Evaluation+1
AskPDF
Jun 22, 2026

Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation

Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that provide reward signals, ranking decisions, and data-filtering criteria. Yet VLMs differ substantially in training data and architecture, encoding physical phenomena through distinct internal representations. A single global evaluation schema therefore gives every VLM the same axes of competence, regardless of what each can actually perceive. We propose JudgeFit, an iterative refinement procedure that discovers a per-VLM evaluation taxonomy. An initial taxonomy is constructed by prompting the target VLM to enumerate physics errors on a small set of videos and clustering the resulting descriptions. The taxonomy is then refined through a diagnostic step: we calibrate the VLM's per-dimension scores to human physical-commonsense ratings, diagnose which dimensions it scores unreliably or redundantly, and prompt an LLM to repair them, iterating until convergence. We further instantiate this procedure as a benchmark and apply it to 16 VLMs spanning eight model families. The refined taxonomy outperforms the global-schema baseline on held-out videos for every VLM tested, with a mean relative improvement of approximately 32%. Beyond aggregate accuracy, the per-VLM profiles expose model-specific blind spots that overall rankings cannot anticipate, with reliability patterns differing markedly across model families.

Yu Cao, Ziquan Liu, Zhensong Zhang +3

Queen Mary University of London · Huawei Darwin Research Center · Imperial College London

VLM EvaluationPhysical Consistency in Video GenerationVision-Language ModelsVideo-Language Model EvaluationVision-Language Model-as-a-JudgeVLM Calibration+1
AskPDF
Jun 19, 2026

Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models

Do people perceive the same facial expression in the same way? Should we expect vision models to be flexible in how they perceive facial expressions? Facial expressions are nonverbal social signals used in human interaction, but facial expression recognition datasets often focus on a single deterministic annotation per sample. We introduce Chehre, an emoji-prompted video dataset with a wide range of dynamic facial expressions for exploring perceptual variation. In Chehre, 203 participants were prompted to express and record 40 facial emojis. Later, their facial motions were transferred onto synthetic faces to preserve privacy. A separate group annotated the videos, resulting in 2,111 videos annotated by 1,242 perceivers, with ~30 annotators per video. Chehre enables us to define a new task: "distributional expression recognition", which tests whether a model can reproduce the variation observed across annotator responses. We test a selection of video language models on our task. Interestingly, we find that persona prompting can act as a controllable way to shift model perception while helping models better capture the variation observed across human annotators. The dataset and code are available at https://chehre-dataset.github.io/.

Bita Azari, Zoe Stanley, Avneet Batra +4

Simon Fraser University, Canada

VLM EvaluationVideo-Language Model EvaluationFacial Expression RecognitionPersona PromptingMultimodal Model EvaluationPrompt Engineering
AskPDF
Jun 8, 2026

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios. Extensive experiments show that Ego-MC-Bench is highly challenging for state-of-the-art video LLMs. We argue that a key reason is the limited availability of training data for fine-tuning models on this task. Although there exists a wide range of cooking video datasets, existing datasets lack examples of mistakes along with appropriately timed interventions. To help address this data limitation, we also introduce Ego-CoMist, a counterfactual synthetic dataset created by transforming non -interactive cooking videos into supervised training examples showing proactive interventions. We show that fine-tuning on Ego-CoMist yields performance gains especially for smaller and more efficient video LLMs that are well suited for delivering assistance on edge devices.

Apratim Bhattacharyya, Shweta Mahajan, Sanjay Haresh +5

Qualcomm AI Research · York University · Vector Institute for AI

LLM Fine-TuningSynthetic Data GenerationVideo-Language Model EvaluationVideo-Language ModelsMultimodal Model Evaluation
AskPDF
Jun 3, 2026

VCIFBench: Evaluating Complex Instruction Following for Video Understanding

Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether models can satisfy explicit output constraints. We introduce VCIFBench, a benchmark for evaluating complex instruction following in video understanding. VCIFBench constructs constraint-rich instructions from both benchmark-adapted and directly video-grounded prompts, covering content, format, style, and structure requirements, and evaluates model outputs with a hybrid verification pipeline. The benchmark contains 306 satisfiable test instructions, a 540-pair DPO preference dataset, and a 30-item conflict diagnostic subset. Experiments on 10 MLLMs show that joint constraint satisfaction remains challenging. We further show that DPO training on VCIFBench data can improve instruction-following performance.

Huangchen Xu, Yuan Wu, Yi Chang

School of Artificial Intelligence, Jilin University · 2Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University · 3International Center of Future Science, Jilin University

VLM EvaluationVideo UnderstandingVideo-Language Model EvaluationMultimodal Instruction TuningMultimodal Understanding
AskPDF
May 26, 2026

Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models

A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actually achieve this remains unclear. In this work, we introduce DistractionBench to evaluate whether VideoLLMs can robustly link subjects and events in the presence of unrelated video segments. Through controlled interventions, such as inserting short advertisement clips into longer videos, we show that VideoLLMs frequently hallucinate interactions between entities from different segments, incorrectly attributing actions from injected advertisements to subjects in the main video. We characterize this systematic hallucination as bag-of-events (BoE) behavior, where models process videos as collections of events rather than temporally structured sequences. Evaluating 11 popular VideoLLMs, we find that all models exhibit substantial BoE behavior. Our findings suggest that VideoLLMs lack reliable mechanisms for temporal grounding and motivate the development of models with more robust subject-event association.

Oscar Chew, Serhii Honcharenko, Qian-Hui Chen +4

Texas A&M University · National Taiwan University · Stanford University +1

Temporal Video GroundingVideo-Language Model EvaluationVideo-Language ModelsMultimodal Model EvaluationTemporal Video Understanding
AskPDF
May 13, 2026

When Vision Speaks for Sound

Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate acoustic information, rather than verifying the audio stream. This issue appears across both state-of-the-art open-source omni models and leading closed-source models from providers such as Google and OpenAI. We characterize this failure mode as an audio-visual Clever Hans effect, in which models appear (falsely) audio-grounded, but actually exploit visual-acoustic correlations without verifying whether the audio and visual streams are truly aligned. To systematically study this behavior, we introduce Thud, an intervention-driven probing framework based on three counterfactual audio edits: Shift, which tests temporal synchronization; Mute, which tests sound existence; and Swap, which tests audio-visual consistency. Beyond diagnosis, we further study a two-stage alignment recipe: intervention-derived preference pairs teach audio verification, while event-level general video preferences regularize the model against over-specialization. Our best 10K-sample recipe improves average performance across the three intervention dimensions by 28 percentage points, while slightly improving performance on general video and audio-visual QA benchmarks.

Xiaofei Wen, Wenjie Jacky Mo, Xingyu Fu +6

dUniversity of California, Davis · pPrinceton University · wUniversity of Wisconsin–Madison +1

Audio-Language Model EvaluationAudio-Visual UnderstandingVideo-Language Model EvaluationAudio ReasoningAudio UnderstandingVideo-Language Models+5
AskPDF
May 11, 2026

EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant

Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most video-language models (VideoLLMs) are trained for offline inference, and existing streaming benchmarks externalize this timing decision to the evaluator. We address this gap with RealStreamEval, a frame-level multi-turn evaluation protocol that exposes models to sequential observations and penalizes unnecessary responses. Under this protocol, we observed that strong offline VideoLLMs retain useful visual understanding but lack an interaction policy for deciding when to respond. Motivated by this observation, we propose EvoStreaming, a self-evolved streaming adaptation framework in which the base model itself acts as data generator, relevance annotator, and roll-out policy to synthesize streaming trajectories without external supervision. With only 1,0001{,}000 self-generated samples (139×139\times less than the leading streaming instruction-tuning approach) and no architectural changes, EvoStreaming consistently improves the overall RealStreamEval score by up to 10.810.8 points across five open VideoLLM backbones (Qwen2/2.5/3-VL, InternVL-3.5, MiniCPM-V4.5) while largely preserving offline video performance. These results suggest that data-efficient interaction tuning is a practical path for adapting existing VideoLLMs to streaming assistants.

Zichen Wen, Boxue Yang, Junlong Ke +5

EPIC Lab, Shanghai Jiao Tong University · Tsinghua University · The Hong Kong University of Science and Technology (Guangzhou) +1

Streaming Video UnderstandingSelf-TrainingVideo-Language Model EvaluationVideo-Language ModelsMultimodal Model EvaluationStreaming Inference
AskPDF
May 11, 2026

TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models

Video large language models (Video-LLMs) have made strong progress in general video understanding, but their ability to maintain temporal object consistency remains underexplored. Existing benchmarks often emphasize event recognition, action understanding, or coarse temporal reasoning, while rarely testing whether models can preserve the identity, state, and continuity of the same object across occlusion, disappearance, reappearance, state transitions, and cross-object interactions. We introduce TOC-Bench, a diagnostic benchmark for evaluating temporal object consistency in Video-LLMs. TOC-Bench is object-track grounded: each queried subject is linked to a per-frame trajectory and a structured temporal event timeline. To ensure that questions require temporally ordered visual evidence rather than language priors, single-frame shortcuts, or unordered frame cues, we design a three-layer temporal-necessity filtering protocol, which removes 60.7% of candidate QA pairs and retains 17,900 temporally dependent items across 10 diagnostic dimensions. From this pool, we construct a human-verified benchmark with 2,323 high-quality QA pairs over 1,951 videos. Experiments on representative Video-LLMs show that temporal object consistency remains a major unsolved challenge, with notable weaknesses in event counting, event ordering, identity-sensitive reasoning, and hallucination-aware verification, even when models perform well on general video understanding benchmarks. These results suggest that object-centric temporal coherence is a key bottleneck for current Video-LLMs, and that TOC-Bench provides a focused platform for diagnosing and improving object-aware temporal reasoning. The resource is available at https://github.com/cjzcjz666/toc_bench.git.

Junzhe Chen, Siyuan Meng, Yuxi Chen +3

Tianjin University

Video-Language Model EvaluationVideo-Language ModelsMultimodal Model EvaluationTemporal Video Understanding
AskPDF
Apr 25, 2026

PushupBench: Your VLM is not good at counting pushups

Large vision-language models (VLMs) can recognize what happens in video but fail to count how many times. We introduce PushupBench, 446 long-form clips (avg. 36.7s) for evaluating repetition counting. The best frontier model achieves 42.1% exact accuracy; open-source 4B models score ∼\sim6%, matching supervised baselines. We show that accuracy alone misleads -- weaker models exploit the modal count rather than reason temporally. Fine-tuning on counting with 1k samples transfers to general video understanding: MVBench (+2.15), PerceptionTest (+1.88), TVBench (+4.54), suggesting counting is a proxy for broader temporal reasoning.PushupBench incorporated in lmms-eval (https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/1262) and hosted on (pushupbench.com/)

Shengzhi Li, Jiarun Chen, Karun Sharma +2

Multimodal UnderstandingVideo-Language Model EvaluationLarge Vision-Language ModelsVLM EvaluationTemporal Video UnderstandingVideo Foundation Models+1
AskPDF
Apr 14, 2026

Distorted or Fabricated? A Survey on Hallucination in Video LLMs

Despite significant progress in video-language modeling, hallucinations remain a persistent challenge in Video Large Language Models (Vid-LLMs), referring to outputs that appear plausible yet contradict the content of the input video. This survey presents a comprehensive analysis of hallucinations in Vid-LLMs and introduces a systematic taxonomy that categorizes them into two core types: dynamic distortion and content fabrication, each comprising two subtypes with representative cases. Building on this taxonomy, we review recent advances in the evaluation and mitigation of hallucinations, covering key benchmarks, metrics, and intervention strategies. We further analyze the root causes of dynamic distortion and content fabrication, which often result from limited capacity for temporal representation and insufficient visual grounding. These insights inform several promising directions for future work, including the development of motion-aware visual encoders and the integration of counterfactual learning techniques. This survey consolidates scattered progress to foster a systematic understanding of hallucinations in Vid-LLMs, laying the groundwork for building robust and reliable video-language systems. An up-to-date curated list of related works is maintained at https://github.com/hukcc/Awesome-Video-Hallucination .

Yiyang Huang, Yitian Zhang, Yizhou Wang +4

Department of Electrical and Computer Engineering, Northeastern University · Khoury College of Computer Science, Northeastern University

VLM HallucinationVideo-Language ModelsVLM Hallucination MitigationVideo-Language Model Evaluation
AskPDF
Apr 13, 2026

OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video

Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form cinematic videos into detailed, temporally grounded scripts remains a significant challenge. This paper introduces the novel video-to-script (V2S) task, aiming to generate hierarchical, scene-by-scene scripts encompassing character actions, dialogues, expressions, and audio cues. To facilitate this, we construct a first-of-its-kind human-annotated benchmark and propose a temporally-aware hierarchical evaluation framework. Furthermore, we present OmniScript, an 8B-parameter omni-modal (audio-visual) language model tailored for long-form narrative comprehension. OmniScript is trained via a progressive pipeline that leverages chain-of-thought supervised fine-tuning for plot and character reasoning, followed by reinforcement learning using temporally segmented rewards. Extensive experiments demonstrate that despite its parameter efficiency, OmniScript significantly outperforms larger open-source models and achieves performance comparable to state-of-the-art proprietary models, including Gemini 3-Pro, in both temporal localization and multi-field semantic accuracy.

Junfu Pu, Yuxin Chen, Teng Wang +1

ARC Lab, Tencent

Long-Video UnderstandingMultimodal Large Language ModelsTemporal Video UnderstandingVideo-Language Model Evaluation
AskPDF
Apr 11, 2026

LVSum: A Benchmark for Timestamp-Aware Long Video Summarization

Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded. We introduce LVSum, a human-annotated benchmark for evaluating long-form video summarization with fine-grained temporal alignment. LVSum comprises 72 diverse videos spanning 13 domains with an average duration of 16 minutes, each annotated with up to 10 human-generated summaries containing temporal references. We conduct a comprehensive evaluation of leading proprietary and open-source MLLMs using newly introduced LLM-based metrics for content relevance and modality coherence, alongside standard automatic metrics. Our experiments reveal three key findings: (1) transcripts contribute substantially more to summarization quality than visual frames alone, (2) a significant performance gap persists between model-generated and human-written summaries, and (3) current MLLMs exhibit systematic weaknesses in temporal grounding, instruction adherence, and cross-modal coherence. We release the dataset and code.

Alkesh Patel, Melis Ozyildirim, Ying-Chang Cheng +1

Apple

Video SummarizationVideo-Language Model EvaluationMultimodal Large Language ModelsTemporal Video Grounding
AskPDF
Apr 10, 2026

SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos

Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing interactions update the procedural state and thereby determine the correctness of later actions. We introduce SiMing-Bench, the first benchmark for evaluating this capability from full-length clinical skill videos. It targets rubric-grounded process-level judgment of whether interaction-driven state updates preserve procedural correctness across an entire workflow. SiMing-Bench is instantiated with SiMing-Score, a physician-annotated dataset of real clinical skill examination videos spanning cardiopulmonary resuscitation, automated external defibrillator operation, and bag-mask ventilation, each paired with a standardized step-wise rubric and dual-expert labels. Across diverse open- and closed-source MLLMs, we observe consistently weak agreement with physician judgments. Moreover, weak performance on rubric-defined intermediate steps persists even when overall procedure-level correlation appears acceptable, suggesting that coarse global assessment substantially overestimates current models' procedural judgment ability. Additional analyses with binary step judgment and step-aligned clips indicate that the bottleneck is not merely fine-grained scoring or temporal localization, but modeling how continuous interactions update procedural state over time.

Xiyang Huang, Jiawei Lin, Keying Wu +9

School of Artificial Intelligence, Wuhan University · Center for Language and Information Research, Wuhan University · Southwest Jiaotong University +3

Video-Language Model EvaluationMultimodal Model EvaluationState Tracking
AskPDF
Apr 10, 2026

How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms

While Multimodal Large Language Models (MLLMs) have advanced Video Temporal Grounding (VTG), existing methods often couple output paradigms with different backbones, datasets, and training protocols. This makes it challenging to isolate the specific impact of the output design. Additionally, as VTG systems are increasingly considered for resource-constrained edge deployment, the trade-off between output formulation and system-level efficiency requires systematic investigation. In this paper, we present a controlled empirical study comparing three dominant VTG output paradigms: Text Numeral Generation, Temporal Token Generation, and Continuous Temporal Decoding. We evaluate these paradigms across identical compact VLMs (SmolVLM2, FastVLM, and Molmo2) using consistent datasets and LoRA fine-tuning protocols. Evaluations on Charades-STA, QVHighlights, and YouCook2 measure both localization accuracy and system efficiency, including inference latency, training throughput, and parameter overhead. Our results demonstrate that the choice of output formulation significantly affects both grounding accuracy and computational cost, independent of model scale. Specifically, the continuous distribution paradigm consistently achieves the most favorable efficiency-accuracy trade-off on the Pareto frontier, delivering robust localization with minimal latency overhead. These findings provide objective empirical guidelines for designing efficient, deployment-ready VTG systems.

Shengji Jin, Yuanhao Zou, Victor Zhu +2

The University of Central Florida · Axon

Temporal Video GroundingEfficient VLM InferenceVideo-Language Model Evaluation
AskPDF
Apr 8, 2026

VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess models in offline settings. In contrast, the performance of a streaming VLM depends on additional metrics beyond pure video understanding, including proactiveness, which reflects the timeliness of the model's responses, and consistency, which captures the robustness of its responses over time. To address this limitation, we propose VSAS-Bench, a new framework and benchmark for Visual Streaming Assistants. In contrast to prior benchmarks that primarily employ single-turn question answering on video inputs, VSAS-Bench features temporally dense annotations with over 18,000 annotations across diverse input domains and task types. We introduce standardized synchronous and asynchronous evaluation protocols, along with metrics that isolate and measure distinct capabilities of streaming VLMs. Using this framework, we conduct large-scale evaluations of recent video and streaming VLMs, analyzing the accuracy-latency trade-off under key design factors such as memory buffer length, memory access policy, and input resolution, yielding several practical insights. Finally, we show empirically that conventional VLMs can be adapted to streaming settings without additional training, and demonstrate that these adapted models outperform recent streaming VLMs. For example, Qwen3-VL-4B surpasses Dispider, the best streaming VLM on our benchmark, by 3% under the asynchronous protocol. The benchmark and code will be available at https://github.com/apple/ml-vsas-bench.

Pavan Kumar Anasosalu Vasu, Cem Koc, Fartash Faghri +6

Apple

VLM EvaluationVideo-Language Model EvaluationStreaming Video Understanding
AskPDF
Apr 6, 2026

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap, we introduce Video-MME-v2, a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding. To systematically evaluate model capabilities, we design a progressive tri-level hierarchy that incrementally increases the complexity of video comprehension, ranging from multi-point visual information aggregation, to temporal dynamics modeling, and ultimately to complex multimodal reasoning. Besides, in contrast to conventional per-question accuracy, we propose a group-based non-linear evaluation strategy that enforces both consistency across related queries and coherence in multi-step reasoning. It penalizes fragmented or guess-based correctness and assigns credit only to answers supported by valid reasoning. To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline, involving 12 annotators and 50 independent reviewers. Backed by 3,300 human-hours and up to 5 rounds of quality assurance, Video-MME-v2 aims to serve as one of the most authoritative video benchmarks. Extensive experiments reveal a substantial gap between current best model Gemini-3-Pro and human experts, and uncover a clear hierarchical bottleneck where errors in visual information aggregation and temporal modeling propagate to limit high-level reasoning. We further find that thinking-based reasoning is highly dependent on textual cues, improving performance with subtitles but sometimes degrading it in purely visual settings. By exposing these limitations, Video-MME-v2 establishes a demanding new testbed for the development of next-generation video MLLMs.

Chaoyou Fu, Haozhi Yuan, Yuhao Dong +16

Video UnderstandingVideo-Language Model EvaluationVLM RobustnessMultimodal ReasoningTemporal Video Understanding
AskPDF
Apr 6, 2026

BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing

Recent multimodal large language models (MLLMs) have shown strong capabilities in general video understanding, driving growing interest in automatic sports commentary generation. However, existing benchmarks for this task focus exclusively on team sports such as soccer and basketball, leaving combat sports entirely unexplored. Notably, combat sports present distinct challenges: critical actions unfold within milliseconds with visually subtle yet semantically decisive differences, and professional commentary contains a substantially higher proportion of tactical analysis compared to team sports. In this paper, we present BoxComm, a large-scale dataset comprising 445 World Boxing Championship match videos with over 52K commentary sentences from professional broadcasts. We propose a structured commentary taxonomy that categorizes each sentence into play-by-play, tactical, or contextual, providing the first category-level annotation for sports commentary benchmarks. Building on this taxonomy, we introduce two novel and complementary evaluations tailored to sports commentary generation: (1) category-conditioned generation, which evaluates whether models can produce accurate commentary of a specified type given video context; and (2) commentary rhythm assessment, which measures whether freely generated commentary exhibits appropriate temporal pacing and type distribution over continuous video segments, capturing a dimension of commentary competence that prior benchmarks have not addressed. Experiments on multiple state-of-the-art MLLMs reveal that current models struggle on both evaluations. We further propose EIC-Gen, an improved baseline incorporating detected punch events to supply structured action cues, yielding consistent gains and highlighting the importance of perceiving fleeting and subtle events for combat sports commentary.

Kaiwen Wang, Kaili Zheng, Rongrong Deng +3

Tsinghua University Beijing, China · Beijing Sport University Beijing, China

Sports Video AnalysisVideo-Language Model Evaluation
AskPDF
Apr 2, 2026

A Simple Baseline for Streaming Video Understanding

Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple finding: a sliding-window baseline that feeds only the most recent N frames to an off-the-shelf VLM already matches or surpasses published streaming models. We formalize this baseline as SimpleStream and evaluate it against 13 major offline and online video LLM baselines on OVO-Bench and StreamingBench. Despite its simplicity, SimpleStream delivers consistently strong performance. With only 4 recent frames, it reaches 67.7% average accuracy on OVO-Bench and 80.59% on StreamingBench. Controlled ablations further show that the value of longer context is backbone-dependent rather than uniformly increasing with model scale, and reveal a consistent perception-memory trade-off: adding more historical context can improve recall, but often weakens real-time perception. This suggests that stronger memory, retrieval, or compression modules should not be taken as evidence of progress unless they clearly outperform SimpleStream under the same protocol. We therefore argue that future streaming benchmarks should separate recent-scene perception from long-range memory, so that performance improvements from added complexity can be evaluated more clearly.

Yujiao Shen, Shulin Tian, Jingkang Yang +1

S-Lab, Nanyang Technological University

Streaming Video UnderstandingStreaming InferenceVideo-Language Model Evaluation
AskPDF
Apr 2, 2026

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

Video multimodal large language models achieve strong results on existing benchmarks, but answer accuracy alone does not establish whether they can locate the evidence needed to answer a question. We introduce VideoZeroBench, a challenging long-video benchmark with manually annotated question-answer pairs spanning 13 video domains. Questions target fine-grained cues, fleeting events, and evidence distributed across multiple segments. Temporal intervals and key-frame boxes are annotated where applicable. All questions undergo two rounds of cross-verification for answer validity and evidence quality. Our five-level diagnostic protocol compares answering with and without evidence hints, then combines answer correctness with independently evaluated temporal and spatial grounding. Across 19 evaluated models, the best standard QA accuracy is 24.8% (Level-3), achieved by Gemini-3.7-Flash. No model exceeds 1.8% when correct answers and accurate spatio-temporal localization are jointly required (Level-5). Analyses of atomic abilities, evidence spans, input modalities, and thinking-with-videos inference further characterize where the evaluated systems struggle. These findings motivate more precise evidence search and localization for long-video question answering. Our code and data are publicly released.

Jiahao Meng, Yue Tan, Qi Xu +9

PKU · WHU · CASIA +2

Video-Language Model EvaluationLong-Video QATemporal Video Grounding
AskPDF
Apr 1, 2026

CL-VISTA: Benchmarking Continual Learning in Video Large Language Models

Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundation models: many still rely on models without large-scale pre-training, and prevailing benchmarks typically partition a single dataset into sub-tasks, resulting in high task redundancy and negligible forgetting on pre-trained Video-LLMs. To address these limitations, we propose CL-VISTA, a benchmark tailored for continual video understanding of Video-LLMs. By curating 8 diverse tasks spanning perception, understanding, and reasoning, CL-VISTA induces substantial distribution shifts that effectively expose catastrophic forgetting. To systematically assess CL methods, we establish a comprehensive evaluation framework comprising 6 distinct protocols across 3 critical dimensions: performance, computational efficiency, and memory footprint. Notably, the performance dimension incorporates a general video understanding assessment to assess whether CL methods genuinely enhance foundational intelligence or merely induce task-specific overfitting. Extensive benchmarking of 10 mainstream CL methods reveals a fundamental trade-off: no single approach achieves universal superiority across all dimensions. Methods that successfully mitigate catastrophic forgetting tend to compromise generalization or incur prohibitive computational and memory overheads. We hope CL-VISTA provides critical insights for advancing continual learning in multimodal foundation models.

Haiyang Guo, Yichen Shi, Fei Zhu +6

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · MAIS, Institute of Automation, Chinese Academy of Sciences · Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, CAS +2

Continual Learning for VLMsVideo-Language Model EvaluationCatastrophic Forgetting
AskPDF
Mar 29, 2026

A Benchmarking Methodology to Assess Open-Source Video Large Language Models in Automatic Captioning of News Videos

News videos are among the most prevalent content types produced by television stations and online streaming platforms, yet generating textual descriptions to facilitate indexing and retrieval largely remains a manual process. Video Large Language Models (VidLLMs) offer significant potential to automate this task, but a comprehensive evaluation in the news domain is still lacking. This work presents a comparative study of eight state-of-the-art open-source VidLLMs for automatic news video captioning, evaluated on two complementary benchmark datasets: a Chilean TV news corpus (approximately 1,345 clips) and a BBC News corpus (9,838 clips). We employ lexical metrics (METEOR, ROUGE-L), semantic metrics (BERTScore, CLIPScore, Text Similarity, Mean Reciprocal Rank), and two novel fidelity metrics proposed in this work: the Thematic Fidelity Score (TFS) and Entity Fidelity Score (EFS). Our analysis reveals that standard metrics exhibit limited discriminative power for news video captioning due to surface-form dependence, static-frame insensitivity, and function-word inflation. TFS and EFS address these gaps by directly assessing thematic structure preservation and named-entity coverage in the generated captions. Results show that Gemma~3 achieves the highest overall performance across both datasets and most evaluation dimensions, with Qwen-VL as a consistent runner-up.

David Miranda Paredes, Jose M. Saavedra, Marcelo Pizarro

Facultad de Ingenier´ıa y Ciencias Aplicadas, Universidad de los Andes, Chile, Av. Monse˜nor ´Alvaro del Portillo 12455, Santiago, 100190, RM, Chile.

Video Caption EvaluationVideo-Language Model EvaluationVideo Captioning
AskPDF
Mar 24, 2026

MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding

The rapid progress of Large Language Models (LLMs) has spurred growing interest in Multi-modal LLMs (MLLMs) and motivated the development of benchmarks to evaluate their perceptual and comprehension abilities. Existing benchmarks, however, are limited to static images or single videos, overlooking the complex interactions across multiple videos. To address this gap, we introduce the Multi-Video Perception Evaluation Benchmark (MVPBench), a new benchmark featuring 14 subtasks across diverse visual domains designed to evaluate models on extracting relevant information from video sequences to make informed decisions. MVPBench includes 5K question-answering tests involving 2.7K video clips sourced from existing datasets and manually annotated clips. Extensive evaluations reveal that current models struggle to process multi-video inputs effectively, underscoring substantial limitations in their multi-video comprehension. We anticipate MVPBench will drive advancements in multi-video perception.

Purui Bai, Tao Wu, Jiayang Sun +3

MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China · SIST, ShanghaiTech University, Shanghai, China

Video UnderstandingVideo-Language Model EvaluationMultimodal Model EvaluationVideo QA
AskPDF
Mar 23, 2026

StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding

Real-time, continuous understanding of visual signals is essential for real-world interactive AI applications, and poses a fundamental system-level challenge. Existing research on streaming video understanding, however, typically focuses on isolated aspects such as question-answering accuracy under limited visual context or improvements in encoding efficiency, while largely overlooking practical deployability under realistic resource constraints. To bridge this gap, we introduce StreamingEval, a unified evaluation framework for assessing the streaming video understanding capabilities of Video-LLMs under realistic constraints. StreamingEval benchmarks both mainstream offline models and recent online video models under a standardized protocol, explicitly characterizing the trade-off between efficiency, storage and accuracy. Specifically, we adopt a fixed-capacity memory bank to normalize accessible historical visual context, and jointly evaluate visual encoding efficiency, text decoding latency, and task performance to quantify overall system deployability. Extensive experiments across multiple datasets reveal substantial gaps between current Video-LLMs and the requirements of realistic streaming applications, providing a systematic basis for future research in this direction. Codes will be released at https://github.com/wwgTang-111/StreamingEval1.

Guowei Tang, Tianwen Qian, Huanran Zheng +2

East China Normal University, Shanghai, China

Streaming Video UnderstandingVideo-Language Model EvaluationEfficient VLM Inference
AskPDF
Mar 20, 2026

Leum-VL Technical Report

A short video succeeds not simply because of what it shows, but because of how it schedules attention -- yet current multimodal models lack the structural grammar to parse or produce this organization. Existing models can describe scenes, answer event-centric questions, and read on-screen text, but they are far less reliable at identifying timeline-grounded units such as hooks, cut rationales, shot-induced tension, and platform-facing packaging cues. We propose SV6D (Structured Video in Six Dimensions), inspired by professional storyboard practice in film and television production, a representation framework that decomposes internet-native video into six complementary structural dimensions -- subject, aesthetics, camera language, editing, narrative, and dissemination -- with each label tied to physically observable evidence on the timeline. We formalize a unified optimization objective over SV6D that combines Hungarian-matched temporal alignment, dimension-wise semantic label distance, and quality regularization. Building on this framework, we present Leum-VL-8B, an 8B video-language model that realizes the SV6D objective through an expert-driven post-training pipeline, further refined through verifiable reinforcement learning on perception-oriented tasks. Leum-VL-8B achieves 70.8 on VideoMME (w/o subtitles), 70.0 on MVBench, and 61.6 on MotionBench, while remaining competitive on general multimodal evaluations such as MMBench-EN. We also construct FeedBench, a benchmark for structure-sensitive short-video understanding. Our results indicate that the missing layer in video AI is not pixel generation but structural representation: grounded on the timeline, linked to visible evidence, and directly consumable by downstream workflows such as editing, retrieval, recommendation, and generation control, including text-heavy internet video formats with overlays and image-text layouts.

Yuxuan He, Chaiming Huang, Yifan Wu +4

Hainan Sihe Data Technology Co., Ltd.

Video UnderstandingVideo-Language ModelsTemporal Video UnderstandingVideo-Language Model Evaluation
AskPDF
Mar 19, 2026

GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?

In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting such content. However, existing evaluation protocols largely treat the task as a binary classification problem and rely on coarse-grained metrics such as overall accuracy, providing limited insight into where LVLMs succeed or fail. To address this limitation, we introduce GenVideoLens, a fine-grained benchmark that enables dimension-wise evaluation of LVLM capabilities in AI-generated video detection. The benchmark contains 400 highly deceptive AI-generated videos and 100 real videos, annotated by experts across 15 authenticity dimensions covering perceptual, optical, physical, and temporal cues. We evaluate eleven representative LVLMs on this benchmark. Our analysis reveals a pronounced dimensional imbalance. While LVLMs perform relatively well on perceptual cues, they struggle with optical consistency, physical interactions, and temporal-causal reasoning. Model performance also varies substantially across dimensions, with smaller open-source models sometimes outperforming stronger proprietary models on specific authenticity cues. Temporal perturbation experiments further show that current LVLMs make limited use of temporal information. Overall, GenVideoLens provides diagnostic insights into LVLM behavior, revealing key capability gaps and offering guidance for improving future AI-generated video detection systems.

Yueying Zou, Pei Pei Li, Zekun Li +4

Beijing University of Posts and Telecommunications, Beijing, China · University of California, Santa Barbara, CA, USA · Center for Research on Intelligent Perception and Computing, NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China

Synthetic Video Detection BenchmarksDeepfake DetectionVideo-Language Model Evaluation
AskPDF
Mar 19, 2026

Seeking Universal Shot Language Understanding Solutions

Shot language understanding (SLU) is crucial for cinematic analysis but remains challenging due to its diverse cinematographic dimensions and subjective expert judgment. While vision-language models (VLMs) have shown strong ability in general visual understanding, recent studies reveal judgment discrepancies between VLMs and film experts on SLU tasks. To address this gap, we introduce SLU-SUITE, a comprehensive training and evaluation suite containing 490K human-annotated QA pairs across 33 tasks spanning six film-grounded dimensions. Using SLU-SUITE, we originally observe two insights into VLM-based SLU from: the model side, which diagnoses key bottlenecks of modules; the data side, which quantifies cross-dimensional influences among tasks. These findings motivate our universal SLU solutions from two complementary paradigms: UniShot, a balanced one-for-all generalist trained via dynamic-balanced data mixing, and AgentShots, a prompt-routed expert cluster that maximizes peak dimension performance. Extensive experiments show that our models outperform task-specific ensembles on in-domain tasks and surpass leading commercial VLMs by 22% on out-of-domain tasks.

Haoxin Liu, Harshavardhan Kamarthi, Zhiyuan Zhao +2

Georgia Institute of Technology · Dolby Laboratories

Video UnderstandingVideo-Language Model EvaluationVideo-Language Models
AskPDF
Mar 12, 2026

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs

Despite rapid progress, Video Large Language Models (Video-LLMs) remain unreliable due to hallucinations, which are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality). Existing benchmarks provide limited coverage of factuality hallucinations and predominantly evaluate models only in clean settings. We introduce INFACT, a diagnostic benchmark comprising 9{,}800 QA instances with fine-grained taxonomies for faithfulness and factuality, spanning real and synthetic videos. INFACT evaluates models in four modes: Base (clean), Visual Degradation, Evidence Corruption, and Temporal Intervention for order-sensitive items. Reliability under induced modes is quantified using Resist Rate (RR) and Temporal Sensitivity Score (TSS). Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes, with evidence corruption reducing stability and temporal intervention yielding the largest degradation. Notably, many open-source baselines exhibit near-zero TSS on factuality, indicating pronounced temporal inertia on order-sensitive questions.

Junqi Yang, Yuecong Min, Jie Zhang +2

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, UCAS

Video-Language Model EvaluationVideo-Language ModelsFaithfulness in VLMsVLM Robustness
AskPDF