{"list":"other","total":51,"rows":[{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"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},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97},{"id":"2510.09608","title":"StreamingVLM: Real-Time Understanding for Infinite Video Streams","created":"2025-10-10","cited_by_count":95},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78},{"id":"2501.13468","title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","created":"2025-01-23","cited_by_count":73},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63},{"id":"2501.00584","title":"Online Video Understanding: OVBench and VideoChat-Online","created":"2024-12-31","cited_by_count":61},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58},{"id":"2505.15269","title":"LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval","created":"2025-05-21","cited_by_count":54},{"id":"2503.22952","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts","created":"2025-03-29","cited_by_count":51},{"id":"2510.18269","title":"StreamingTOM: Streaming Token Compression for Efficient Video Understanding","created":"2025-10-21","cited_by_count":43},{"id":"2601.14724","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","created":"2026-01-21","cited_by_count":41},{"id":"2512.00891","title":"Accelerating Streaming Video Large Language Models via Hierarchical Token Compression","created":"2025-11-30","cited_by_count":37},{"id":"2604.02317","title":"A Simple Baseline for Streaming Video Understanding","created":"2026-04-02","cited_by_count":33},{"id":"2603.02096","title":"FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding","created":"2026-03-02","cited_by_count":28},{"id":"2512.21334","title":"Streaming Video Instruction Tuning","created":"2025-12-24","cited_by_count":26},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21},{"id":"2605.28258","title":"GUI Agents for Continual Game Generation","created":"2026-05-27","cited_by_count":18},{"id":"2511.06499","title":"SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports","created":"2025-11-09","cited_by_count":17},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16},{"id":"2603.03985","title":"RIVER: A Real-Time Interaction Benchmark for Video LLMs","created":"2026-03-04","cited_by_count":14},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10},{"id":"2510.04560","title":"ContextNav: Towards Agentic Multimodal In-Context Learning","created":"2025-10-06","cited_by_count":10},{"id":"2512.12560","title":"StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding","created":"2025-12-14","cited_by_count":10},{"id":"2601.22575","title":"PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios","created":"2026-01-30","cited_by_count":10},{"id":"2508.10264","title":"MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs","created":"2025-08-14","cited_by_count":9},{"id":"2602.00181","title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","created":"2026-01-30","cited_by_count":9},{"id":"2601.15016","title":"LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding","created":"2026-01-21","cited_by_count":8},{"id":"2601.15655","title":"Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams","created":"2026-01-22","cited_by_count":6},{"id":"2603.15600","title":"From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation","created":"2026-03-16","cited_by_count":6},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6}],"next_cursor":null}