{"total":87,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2604.02317","title":"A Simple Baseline for Streaming Video Understanding","created":"2026-04-02","cited_by_count":33,"area":null},{"id":"2603.02096","title":"FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding","created":"2026-03-02","cited_by_count":28,"area":null},{"id":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24,"area":null},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21,"area":null},{"id":"2412.05185","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2506.00993","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2603.16859","title":"SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2510.17364","title":"Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs","created":"2025-10-20","cited_by_count":9,"area":null},{"id":"2603.25072","title":"GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding","created":"2026-03-26","cited_by_count":8,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2606.16353","title":"What Should a Streaming Video Model Remember?","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2508.19650","title":"Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models","created":"2025-08-27","cited_by_count":6,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.12703","title":"SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2509.26360","title":"TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2510.26113","title":"EgoExo-Con: Exploring View-Invariant Video Temporal Understanding","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2605.10343","title":"EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2608.13416","title":"StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs","created":"2026-08-13","cited_by_count":5,"area":null},{"id":"2605.17921","title":"An Efficient Streaming Video Understanding Framework with Agentic Control","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2606.07639","title":"MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2606.19341","title":"Native Active Perception as Reasoning for Omni-Modal Understanding","created":"2026-06-17","cited_by_count":4,"area":null},{"id":"2509.24563","title":"NeMo: Needle in a Montage for Video-Language Understanding","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2602.22779","title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.23186","title":"ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2609.00291","title":"StreamScout: Learning When to Look Deeper for Streaming Video Understanding","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2412.09907","title":"IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2507.09068","title":"Infinite Video Understanding","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2509.08538","title":"MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2512.00885","title":"HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2603.29186","title":"SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2603.30038","title":"Benchmarking PhD-Level Coding in 3D Geometric Computer Vision","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.17260","title":"LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.22678","title":"Swift Sampling: Selecting Temporal Surprises via Taylor Series","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2606.05008","title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.05259","title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.12300","title":"Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.27922","title":"Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.28516","title":"Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2608.07014","title":"Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs","created":"2026-08-07","cited_by_count":2,"area":null},{"id":"2608.22516","title":"TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding","created":"2026-08-23","cited_by_count":2,"area":null},{"id":"2602.11244","title":"Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.20180","title":"Adaptive Greedy Frame Selection for Long Video Understanding","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.22872","title":"ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.08209","title":"OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.14607","title":"ViMU: Benchmarking Video Metaphorical Understanding","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.22907","title":"VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.24253","title":"TuringViT: Making SOTA Vision Transformers Accessible to All","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.26762","title":"ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2606.30220","title":"From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.25300","title":"MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2607.27895","title":"MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2510.05652","title":"SD-MVSum: Script-Driven Multimodal Video Summarization Method and Datasets","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.16209","title":"StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.18362","title":"FeatureFool: Zero-Query Fooling of Video Models via Feature Map","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.00126","title":"QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.12478","title":"Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.20937","title":"Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.07355","title":"TTF: Temporal Token Fusion for Efficient Video-Language Model","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.00508","title":"V-LynX: Token Interface Alignment for Video+X LLMs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.03635","title":"VidMsg: A Benchmark for Implicit Message Inference in Short Videos","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.06532","title":"GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.20077","title":"The Hidden Evolution of Disguised Visual Context inside the VLM","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31326","title":"Bridging Video Understanding and Generation in a Unified Framework","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02096","title":"LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.15778","title":"Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12408","title":"GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.23601","title":"PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.30670","title":"TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.30981","title":"STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32280","title":"HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37345","title":"When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03099","title":"Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05775","title":"InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.15389","title":"VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18535","title":"Meta-Video: Efficient Standardized Evaluation for Video Understanding","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}