{"list":"other","total":157,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159},{"id":"2504.01805","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","created":"2025-04-02","cited_by_count":159},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146},{"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":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137},{"id":"2506.09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","created":"2025-06-11","cited_by_count":136},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109},{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109},{"id":"2505.18079","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","created":"2025-05-23","cited_by_count":98},{"id":"2510.09608","title":"StreamingVLM: Real-Time Understanding for Infinite Video Streams","created":"2025-10-10","cited_by_count":95},{"id":"2504.13180","title":"PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding","created":"2025-04-17","cited_by_count":92},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89},{"id":"2412.12075","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","created":"2024-12-16","cited_by_count":85},{"id":"2501.07888","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","created":"2025-01-14","cited_by_count":81},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"2506.22139","title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","created":"2025-06-27","cited_by_count":80},{"id":"2503.23765","title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","created":"2025-03-31","cited_by_count":79},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76},{"id":"2509.01563","title":"Kwai Keye-VL 1.5 Technical Report","created":"2025-09-01","cited_by_count":73},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73},{"id":"2501.02955","title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","created":"2025-01-06","cited_by_count":70},{"id":"2506.13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","created":"2025-06-16","cited_by_count":68},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"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":"2506.17221","title":"VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning","created":"2025-06-20","cited_by_count":63},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2503.10200","title":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","created":"2025-03-13","cited_by_count":58},{"id":"2505.21334","title":"HoliTom: Holistic Token Merging for Fast Video Large Language Models","created":"2025-05-27","cited_by_count":58},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58},{"id":"2502.10810","title":"SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding","created":"2025-02-15","cited_by_count":57},{"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":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51},{"id":"2503.22952","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts","created":"2025-03-29","cited_by_count":51},{"id":"2504.00883","title":"Improved Visual-Spatial Reasoning via R1-Zero-Like Training","created":"2025-04-01","cited_by_count":51},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50},{"id":"2411.17991","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","created":"2024-11-27","cited_by_count":47},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43},{"id":"2510.18269","title":"StreamingTOM: Streaming Token Compression for Efficient Video Understanding","created":"2025-10-21","cited_by_count":43},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42},{"id":"2505.20256","title":"Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration","created":"2025-05-26","cited_by_count":41},{"id":"2504.04471","title":"VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT","created":"2025-04-06","cited_by_count":38},{"id":"2505.14454","title":"Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models","created":"2025-05-20","cited_by_count":38},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37},{"id":"2506.19225","title":"Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification","created":"2025-06-24","cited_by_count":37},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34},{"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},{"id":"2505.12620","title":"BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation","created":"2025-05-19","cited_by_count":33},{"id":"2508.01875","title":"StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding","created":"2025-08-03","cited_by_count":33},{"id":"2506.02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence","created":"2025-06-03","cited_by_count":31},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28},{"id":"2510.14560","title":"Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video","created":"2025-10-16","cited_by_count":28},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24},{"id":"2502.11775","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","created":"2025-02-17","cited_by_count":24},{"id":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24},{"id":"2506.05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding","created":"2025-06-05","cited_by_count":23},{"id":"2510.18873","title":"DSI-Bench: A Benchmark for Dynamic Spatial Intelligence","created":"2025-10-21","cited_by_count":23},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22},{"id":"2503.12542","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","created":"2025-03-16","cited_by_count":21},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21},{"id":"2510.23603","title":"PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity","created":"2025-10-27","cited_by_count":21},{"id":"2504.07089","title":"OmniCaptioner: One Captioner to Rule Them All","created":"2025-04-09","cited_by_count":20},{"id":"2601.18157","title":"Agentic Very Long Video Understanding","created":"2026-01-26","cited_by_count":20}],"next_cursor":"100"}