{"total":484,"rows":[{"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,"area":"mllm"},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224,"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402,"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":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909,"area":"mllm"},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688,"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":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586,"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":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547,"area":"mllm"},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546,"area":"mllm"},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515,"area":"mllm"},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461,"area":"mllm"},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410,"area":"mllm"},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406,"area":"mllm"},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365,"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":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322,"area":"mllm"},{"id":"2410.17247","title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","created":"2024-10-22","cited_by_count":294,"area":"mllm"},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290,"area":"mllm"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2312.09245","title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","created":"2023-12-14","cited_by_count":233,"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":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","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":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217,"area":"mllm"},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216,"area":"mllm"},{"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":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197,"area":"mllm"},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195,"area":"mllm"},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167,"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":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160,"area":"mllm"},{"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,"area":"mllm"},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147,"area":"mllm"},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144,"area":"mllm"},{"id":"2405.05803","title":"Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference","created":"2024-05-09","cited_by_count":139,"area":"mllm"},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138,"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":"2402.05935","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","created":"2024-02-08","cited_by_count":131,"area":"mllm"},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126,"area":"mllm"},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125,"area":"mllm"},{"id":"2312.00438","title":"Dolphins: Multimodal Language Model for Driving","created":"2023-12-01","cited_by_count":124,"area":"mllm"},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119,"area":"mllm"},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118,"area":"mllm"},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115,"area":"mllm"},{"id":"2307.08581","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","created":"2023-07-17","cited_by_count":114,"area":"mllm"},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"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":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108,"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":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102,"area":"mllm"},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101,"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":"2310.08825","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","created":"2023-10-13","cited_by_count":98,"area":"mllm"},{"id":"2408.14023","title":"Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos","created":"2024-08-26","cited_by_count":98,"area":"mllm"},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96,"area":"mllm"},{"id":"2506.10967","title":"Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs","created":"2025-06-12","cited_by_count":96,"area":"mllm"},{"id":"2402.10828","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","created":"2024-02-16","cited_by_count":92,"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":"2412.00447","title":"ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models","created":"2024-11-30","cited_by_count":89,"area":"mllm"},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89,"area":"mllm"},{"id":"2404.18532","title":"MileBench: Benchmarking MLLMs in Long Context","created":"2024-04-29","cited_by_count":88,"area":"mllm"},{"id":"2406.11815","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","created":"2024-06-17","cited_by_count":87,"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":"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":"2506.22139","title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","created":"2025-06-27","cited_by_count":80,"area":"mllm"},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"id":"2401.00988","title":"Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models","created":"2024-01-02","cited_by_count":76,"area":"mllm"},{"id":"2406.11069","title":"WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences","created":"2024-06-16","cited_by_count":76,"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":"2406.20098","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","created":"2024-06-28","cited_by_count":74,"area":"mllm"},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72,"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":"2402.11941","title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","created":"2024-02-19","cited_by_count":70,"area":"mllm"},{"id":"2411.18211","title":"TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability","created":"2024-11-27","cited_by_count":70,"area":"mllm"},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70,"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":"2401.10727","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","created":"2024-01-19","cited_by_count":69,"area":"mllm"},{"id":"2404.07214","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","created":"2024-02-20","cited_by_count":68,"area":"mllm"},{"id":"2406.12235","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","created":"2024-06-18","cited_by_count":64,"area":"mllm"},{"id":"2501.00584","title":"Online Video Understanding: OVBench and VideoChat-Online","created":"2024-12-31","cited_by_count":61,"area":"mllm"},{"id":"2501.08282","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","created":"2025-01-14","cited_by_count":59,"area":"mllm"},{"id":"2403.02910","title":"ImgTrojan: Jailbreaking Vision-Language Models with ONE Image","created":"2024-03-05","cited_by_count":57,"area":"mllm"},{"id":"2408.01319","title":"A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks","created":"2024-08-02","cited_by_count":57,"area":"mllm"},{"id":"2409.16597","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","created":"2024-09-25","cited_by_count":57,"area":"mllm"},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2408.16730","title":"VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation","created":"2024-08-29","cited_by_count":55,"area":"mllm"},{"id":"2402.12048","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","created":"2024-02-19","cited_by_count":54,"area":"mllm"},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53,"area":"mllm"},{"id":"2410.12787","title":"The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio","created":"2024-10-16","cited_by_count":53,"area":"mllm"},{"id":"2411.09968","title":"Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs","created":"2024-11-15","cited_by_count":52,"area":"mllm"},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51,"area":"mllm"},{"id":"2411.04923","title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","created":"2024-11-07","cited_by_count":51,"area":"mllm"},{"id":"2405.19315","title":"Matryoshka Query Transformer for Large Vision-Language Models","created":"2024-05-29","cited_by_count":50,"area":"mllm"}],"next_cursor":"100"}