{"total":57,"rows":[{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220,"area":"mllm"},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211,"area":"mllm"},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139,"area":"agents"},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"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":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88,"area":"mllm"},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58,"area":"mllm"},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2503.13646","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","created":"2025-03-17","cited_by_count":44,"area":"mllm"},{"id":"2501.02885","title":"MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs","created":"2025-01-06","cited_by_count":43,"area":null},{"id":"2410.06166","title":"Temporal Reasoning Transfer from Text to Video","created":"2024-10-08","cited_by_count":38,"area":"lr"},{"id":"2503.13139","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","created":"2025-03-17","cited_by_count":34,"area":null},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"id":"2503.12772","title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","created":"2025-03-17","cited_by_count":30,"area":"mllm"},{"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":"2503.13956","title":"Improving LLM Video Understanding with 16 Frames Per Second","created":"2025-03-18","cited_by_count":26,"area":"mllm"},{"id":"2505.17702","title":"Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek","created":"2025-05-23","cited_by_count":24,"area":"lr"},{"id":"2506.05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding","created":"2025-06-05","cited_by_count":23,"area":"mllm"},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"area":null},{"id":"2505.02064","title":"RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video","created":"2025-05-04","cited_by_count":21,"area":"lr"},{"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":"2503.10742","title":"Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing","created":"2025-03-13","cited_by_count":18,"area":"mllm"},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13,"area":null},{"id":"2510.13891","title":"K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding","created":"2025-10-14","cited_by_count":11,"area":"mllm"},{"id":"2410.05714","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2510.13251","title":"Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs","created":"2025-10-15","cited_by_count":10,"area":"mllm"},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"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":"2504.14096","title":"VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment","created":"2025-04-18","cited_by_count":8,"area":"alignment"},{"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":"2412.00624","title":"VideoSAVi: Self-Aligned Video Language Models without Human Supervision","created":"2024-12-01","cited_by_count":7,"area":"alignment"},{"id":"2506.08708","title":"PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly","created":"2025-06-10","cited_by_count":7,"area":"mllm"},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2503.21824","title":"Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations","created":"2025-03-26","cited_by_count":5,"area":"safety"},{"id":"2506.10516","title":"CogStream: Context-guided Streaming Video Question Answering","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2508.17686","title":"Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing","created":"2025-08-25","cited_by_count":5,"area":"mllm"},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2510.11129","title":"video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2410.19896","title":"FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content Analysis","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2504.05491","title":"REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2506.05395","title":"TriPSS: A Tri-Modal Keyframe Extraction Framework Using Perceptual, Structural, and Semantic Representations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2602.08861","title":"TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models","created":"2026-02-09","cited_by_count":2,"area":"mllm"},{"id":"2503.15176","title":"A Review on Large Language Models for Visual Analytics","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2504.14875","title":"ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2509.23433","title":"SPIKE-RL: Video-LLMs meet Bayesian Surprise","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.06509","title":"From Captions to Keyframes: KeyScore for Multimodal Frame Scoring and Video-Language Understanding","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2510.13042","title":"SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models","created":"2025-10-14","cited_by_count":1,"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":"2605.13080","title":"Learning to See What You Need: Gaze Attention for Multimodal Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"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":"2608.15058","title":"MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring","created":"2026-08-15","cited_by_count":0,"area":"mllm"}],"next_cursor":null}