{"total":118,"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":"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":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356,"area":"mllm"},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"area":null},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213,"area":"mllm"},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182,"area":"mllm"},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117,"area":"inference"},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"id":"2406.16338","title":"VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models","created":"2024-06-24","cited_by_count":90,"area":"mllm"},{"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":"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,"area":"mllm"},{"id":"2503.21483","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding","created":"2025-03-27","cited_by_count":75,"area":"mllm"},{"id":"2505.21334","title":"HoliTom: Holistic Token Merging for Fast Video Large Language Models","created":"2025-05-27","cited_by_count":58,"area":"inference"},{"id":"2502.10810","title":"SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding","created":"2025-02-15","cited_by_count":57,"area":"mllm"},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56,"area":"diffusion"},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2410.18967","title":"Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms","created":"2024-10-24","cited_by_count":51,"area":null},{"id":"2503.22952","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts","created":"2025-03-29","cited_by_count":51,"area":"mllm"},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47,"area":"safety"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2410.16267","title":"xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs","created":"2024-10-21","cited_by_count":34,"area":"mllm"},{"id":"2412.14006","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","created":"2024-12-18","cited_by_count":31,"area":"mllm"},{"id":"2510.14032","title":"Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding","created":"2025-10-15","cited_by_count":31,"area":"lr"},{"id":"2409.18938","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","created":"2024-09-27","cited_by_count":30,"area":"lr"},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28,"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":"2512.20618","title":"LongVideoAgent: Multi-Agent Reasoning with Long Videos","created":"2025-12-23","cited_by_count":25,"area":"lr"},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2406.08725","title":"RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs","created":"2024-06-13","cited_by_count":23,"area":"alignment"},{"id":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2412.00161","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","created":"2024-11-29","cited_by_count":22,"area":"lr"},{"id":"2406.10326","title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","created":"2024-06-14","cited_by_count":20,"area":null},{"id":"2406.19875","title":"InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows","created":"2024-06-28","cited_by_count":20,"area":"mllm"},{"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":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18,"area":"lr"},{"id":"2505.24867","title":"Time Blindness: Why Video-Language Models Can't See What Humans Can?","created":"2025-05-30","cited_by_count":18,"area":"mllm"},{"id":"2503.09149","title":"Memory-enhanced Retrieval Augmentation for Long Video Understanding","created":"2025-03-12","cited_by_count":17,"area":"rag"},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.16257","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","created":"2025-03-20","cited_by_count":13,"area":"inference"},{"id":"2406.09781","title":"GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2411.16156","title":"VideoOrion: Tokenizing Object Dynamics in Videos","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2502.15393","title":"LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models","created":"2025-02-21","cited_by_count":11,"area":"mllm"},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2508.14160","title":"RynnEC: Bringing MLLMs into Embodied World","created":"2025-08-19","cited_by_count":11,"area":"mllm"},{"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":"2511.15690","title":"MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping","created":"2025-11-19","cited_by_count":11,"area":"mllm"},{"id":"2603.05075","title":"UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark","created":"2026-03-05","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":"2501.05067","title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","created":"2025-01-09","cited_by_count":10,"area":"mllm"},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2503.18422","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding","created":"2025-03-24","cited_by_count":8,"area":null},{"id":"2505.20027","title":"Multi-modal brain encoding models for multi-modal stimuli","created":"2025-05-26","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":"2412.20613","title":"Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study","created":"2024-12-29","cited_by_count":7,"area":"mllm"},{"id":"2505.13860","title":"Domain Adaptation of VLM for Soccer Video Understanding","created":"2025-05-20","cited_by_count":7,"area":"mllm"},{"id":"2503.08576","title":"RAG-Adapter: A Plug-and-Play RAG-enhanced Framework for Long Video Understanding","created":"2025-03-11","cited_by_count":6,"area":"mllm"},{"id":"2503.20472","title":"From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment","created":"2025-03-26","cited_by_count":6,"area":"mllm"},{"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":"2411.10557","title":"MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models","created":"2024-11-15","cited_by_count":5,"area":"mllm"},{"id":"2501.07227","title":"MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning","created":"2025-01-13","cited_by_count":5,"area":"lr"},{"id":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2602.03890","title":"4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2604.14149","title":"One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding","created":"2026-04-15","cited_by_count":5,"area":"mllm"},{"id":"2505.17090","title":"EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2512.13238","title":"Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2604.05079","title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2508.10287","title":"JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2509.01337","title":"LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition","created":"2025-09-01","cited_by_count":3,"area":"lr"},{"id":"2511.23377","title":"DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted Baseline","created":"2025-11-28","cited_by_count":3,"area":"diffusion"},{"id":"2412.17415","title":"VidCtx: Context-aware Video Question Answering with Image Models","created":"2024-12-23","cited_by_count":2,"area":"mllm"},{"id":"2501.16786","title":"Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding","created":"2025-01-28","cited_by_count":2,"area":"mllm"},{"id":"2503.19281","title":"CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language Model","created":"2025-03-25","cited_by_count":2,"area":"mllm"},{"id":"2508.02134","title":"Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference","created":"2025-08-04","cited_by_count":2,"area":"mllm"},{"id":"2508.09789","title":"Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations","created":"2025-08-13","cited_by_count":2,"area":"mllm"},{"id":"2509.13161","title":"Enhancing Video Large Language Models with Structured Multi-Video Collaborative Reasoning","created":"2025-09-16","cited_by_count":2,"area":"lr"},{"id":"2511.21998","title":"Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?","created":"2025-11-27","cited_by_count":2,"area":"mllm"},{"id":"2512.08410","title":"Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval","created":"2025-12-09","cited_by_count":2,"area":"mllm"},{"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":"2603.13412","title":"WAT: Online Video Understanding Needs Watching Before Thinking","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"id":"2604.01881","title":"HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2606.17798","title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","created":"2026-06-16","cited_by_count":2,"area":"inference"},{"id":"2607.27826","title":"Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2412.04806","title":"NeST: Neighborhood-aware semantic alignment and temporal modulation for LLM based time series forecasting","created":"2024-12-06","cited_by_count":1,"area":null},{"id":"2501.17391","title":"LFTR: Learning-Free Token Reduction for Multimodal Large Language Models","created":"2025-01-29","cited_by_count":1,"area":"mllm"},{"id":"2503.00049","title":"Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2505.13062","title":"Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model","created":"2025-05-19","cited_by_count":1,"area":"mllm"},{"id":"2506.05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2507.06072","title":"MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding","created":"2025-07-08","cited_by_count":1,"area":"driving"},{"id":"2508.08989","title":"KFFocus: Highlighting Keyframes for Enhanced Video Understanding","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2509.21291","title":"VC-Agent: An Interactive Agent for Customized Video Dataset Collection","created":"2025-09-25","cited_by_count":1,"area":"agents"},{"id":"2602.01649","title":"Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.13268","title":"Indexing Multimodal Language Models for Large-scale Image Retrieval","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"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}],"next_cursor":"100"}