{"total":233,"rows":[{"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,"area":"mllm"},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719,"area":"mllm"},{"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,"area":"mllm"},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665,"area":"mllm"},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410,"area":"mllm"},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356,"area":"mllm"},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309,"area":"mllm"},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229,"area":"mllm"},{"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":"2503.02175","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","created":"2025-03-04","cited_by_count":181,"area":"mllm"},{"id":"2501.03895","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","created":"2025-01-07","cited_by_count":166,"area":"mllm"},{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147,"area":"mllm"},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146,"area":"mllm"},{"id":"2408.15542","title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input","created":"2024-08-28","cited_by_count":134,"area":"mllm"},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106,"area":"mllm"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"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":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84,"area":"mllm"},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81,"area":"mllm"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2406.04334","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","created":"2024-06-06","cited_by_count":75,"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":"2406.11303","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","created":"2024-06-17","cited_by_count":72,"area":"mllm"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"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,"area":"mllm"},{"id":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68,"area":"mllm"},{"id":"2501.00584","title":"Online Video Understanding: OVBench and VideoChat-Online","created":"2024-12-31","cited_by_count":61,"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":"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":"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":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"id":"2503.18478","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding","created":"2025-03-24","cited_by_count":49,"area":"mllm"},{"id":"2504.08966","title":"PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models","created":"2025-04-11","cited_by_count":49,"area":"mllm"},{"id":"2501.02189","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","created":"2025-01-04","cited_by_count":47,"area":"mllm"},{"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":"2412.03248","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","created":"2024-12-04","cited_by_count":43,"area":"mllm"},{"id":"2510.18269","title":"StreamingTOM: Streaming Token Compression for Efficient Video Understanding","created":"2025-10-21","cited_by_count":43,"area":"mllm"},{"id":"2601.14724","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","created":"2026-01-21","cited_by_count":41,"area":"mllm"},{"id":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39,"area":"mllm"},{"id":"2406.09367","title":"Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs","created":"2024-06-13","cited_by_count":37,"area":"mllm"},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37,"area":"mllm"},{"id":"2503.06157","title":"UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces","created":"2025-03-08","cited_by_count":36,"area":"mllm"},{"id":"2503.19951","title":"Audio-centric Video Understanding Benchmark without Text Shortcut","created":"2025-03-25","cited_by_count":36,"area":"mllm"},{"id":"2511.21471","title":"SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition","created":"2025-11-26","cited_by_count":35,"area":"mllm"},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2412.09530","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","created":"2024-12-12","cited_by_count":32,"area":"mllm"},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30,"area":"mllm"},{"id":"2503.13983","title":"SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability","created":"2025-03-18","cited_by_count":28,"area":"mllm"},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2504.17447","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","created":"2025-04-24","cited_by_count":27,"area":"mllm"},{"id":"2504.16083","title":"MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention","created":"2025-04-22","cited_by_count":26,"area":"mllm"},{"id":"2506.21862","title":"LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs","created":"2025-06-27","cited_by_count":26,"area":"mllm"},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2410.07177","title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA","created":"2024-10-09","cited_by_count":24,"area":"mllm"},{"id":"2412.08646","title":"StreamChat: Chatting with Streaming Video","created":"2024-12-11","cited_by_count":24,"area":"mllm"},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"id":"2509.07447","title":"In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting","created":"2025-09-09","cited_by_count":22,"area":"mllm"},{"id":"2406.14129","title":"Towards Event-oriented Long Video Understanding","created":"2024-06-20","cited_by_count":21,"area":"mllm"},{"id":"2503.08221","title":"EgoBlind: Towards Egocentric Visual Assistance for the Blind","created":"2025-03-11","cited_by_count":21,"area":"mllm"},{"id":"2506.05287","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","created":"2025-06-05","cited_by_count":21,"area":"mllm"},{"id":"2508.10729","title":"EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering","created":"2025-08-14","cited_by_count":21,"area":"mllm"},{"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":"2412.09501","title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","created":"2024-12-12","cited_by_count":20,"area":"mllm"},{"id":"2503.12496","title":"Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?","created":"2025-03-16","cited_by_count":20,"area":"mllm"},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20,"area":"mllm"},{"id":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19,"area":"mllm"},{"id":"2501.05031","title":"ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark","created":"2025-01-09","cited_by_count":19,"area":"mllm"},{"id":"2503.16036","title":"Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":19,"area":"mllm"},{"id":"2411.13281","title":"VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation","created":"2024-11-20","cited_by_count":18,"area":"mllm"},{"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":"2603.24558","title":"LensWalk: Agentic Video Understanding by Planning How You See in Videos","created":"2026-03-25","cited_by_count":17,"area":"mllm"},{"id":"2503.07298","title":"ALLVB: All-in-One Long Video Understanding Benchmark","created":"2025-03-10","cited_by_count":16,"area":"mllm"},{"id":"2504.15280","title":"Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs","created":"2025-04-21","cited_by_count":16,"area":"mllm"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2402.16050","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","created":"2024-02-25","cited_by_count":14,"area":"mllm"},{"id":"2411.14401","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","created":"2024-11-21","cited_by_count":13,"area":"mllm"},{"id":"2510.08559","title":"SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models","created":"2025-10-09","cited_by_count":13,"area":"mllm"},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2506.15635","title":"FindingDory: A Benchmark to Evaluate Memory in Embodied Agents","created":"2025-06-18","cited_by_count":12,"area":"mllm"},{"id":"2412.06263","title":"iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models","created":"2024-12-09","cited_by_count":11,"area":"mllm"},{"id":"2503.17736","title":"V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction","created":"2025-03-22","cited_by_count":11,"area":"mllm"},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2505.12312","title":"Visuospatial Cognitive Assistant","created":"2025-05-18","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":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"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":"2504.01328","title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models","created":"2025-04-02","cited_by_count":10,"area":"mllm"},{"id":"2505.24158","title":"Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders","created":"2025-05-30","cited_by_count":10,"area":"mllm"},{"id":"2508.12687","title":"EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding","created":"2025-08-18","cited_by_count":10,"area":"mllm"},{"id":"2508.21496","title":"ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding","created":"2025-08-29","cited_by_count":10,"area":"mllm"},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9,"area":"mllm"}],"next_cursor":"100"}