{"total":106,"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":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2512.14699","title":"MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives","created":"2025-12-16","cited_by_count":45,"area":null},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28,"area":null},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28,"area":null},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"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":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25,"area":null},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19,"area":null},{"id":"2406.02547","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","created":"2024-06-04","cited_by_count":17,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13,"area":null},{"id":"2501.05037","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","created":"2025-01-09","cited_by_count":13,"area":null},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11,"area":null},{"id":"2411.12355","title":"DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding","created":"2024-11-19","cited_by_count":10,"area":null},{"id":"2508.11576","title":"Causality Matters: How Temporal Information Emerges in Video Language Models","created":"2025-08-15","cited_by_count":10,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","cited_by_count":9,"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":"2503.10719","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2512.14273","title":"Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","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":"2503.06053","title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"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":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2508.04546","title":"Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Grounding","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2601.07290","title":"VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","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":"2603.15302","title":"Generative Video Compression with One-Dimensional Latent Representation","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.13803","title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2607.13298","title":"FOLIO: Focused Semantic Memory for Streaming Video Understanding","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2608.30294","title":"Dynamic Hub-and-Spoke Memory for Streaming Video Understanding","created":"2026-08-31","cited_by_count":4,"area":null},{"id":"2503.16413","title":"M3: 3D-Spatial MultiModal Memory","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2603.04349","title":"FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering","created":"2026-03-04","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":"2511.06475","title":"NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2602.23294","title":"Towards Long-Form Spatio-Temporal Video Grounding","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2604.19564","title":"EgoSelf: From Memory to Personalized Egocentric Assistant","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2606.27499","title":"DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection","created":"2026-06-25","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":"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":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2504.21403","title":"Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2507.06603","title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2604.14692","title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.19075","title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.06991","title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2609.18540","title":"SVMemAgent: A Streaming Video Memory Agent for Query-Agnostic Online Frame Selection","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2406.03015","title":"Balancing Performance and Efficiency in Zero-shot Robotic Navigation","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2504.15921","title":"ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2508.01270","title":"SGCap: Decoding Semantic Group for Zero-shot Video Captioning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.20178","title":"PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.15066","title":"Tracking spatial temporal details in ultrasound long video via wavelet analysis and memory bank","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2512.16727","title":"OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.20887","title":"Scene Graph-guided SegCaptioning Transformer with Fine-grained Alignment for Controllable Video Segmentation and Captioning","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2603.27259","title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.08077","title":"AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.13651","title":"NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","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":"2606.22804","title":"CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.23256","title":"P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.26515","title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.09759","title":"ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.22078","title":"CommandLM: Data driven behavior level descriptor for ego vehicles","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.28678","title":"ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.04866","title":"Persistent Object Narratives for Token-Efficient Video Language Models","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.07067","title":"DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.11013","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.19723","title":"StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.22975","title":"Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.31005","title":"From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents","created":"2026-08-31","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":"2609.12090","title":"Does Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.19664","title":"VideoResearcher: Self-Improving Tool Design for Long-Video Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20508","title":"Grounded Product Understanding in Livestream Videos","created":"2026-09-17","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":"2609.31665","title":"Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.32592","title":"SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":"100"}