{"total":691,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418,"area":"mllm"},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876,"area":"mllm"},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711,"area":null},{"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":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471,"area":"mllm"},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239,"area":"mllm"},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056,"area":"ssm"},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005,"area":"mllm"},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909,"area":"mllm"},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798,"area":null},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625,"area":null},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550,"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":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490,"area":"driving"},{"id":"2311.17911","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","created":"2023-11-29","cited_by_count":478,"area":"mllm"},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442,"area":null},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398,"area":"mllm"},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393,"area":"diffusion"},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328,"area":"mllm"},{"id":"2401.16420","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","created":"2024-01-29","cited_by_count":326,"area":"mllm"},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"area":"alignment"},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"area":null},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"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":"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":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217,"area":"mllm"},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188,"area":"mllm"},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2309.07915","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","created":"2023-09-14","cited_by_count":172,"area":"mllm"},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2410.22313","title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","created":"2024-10-29","cited_by_count":156,"area":"mllm"},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154,"area":"mllm"},{"id":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150,"area":null},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143,"area":"mllm"},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139,"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":"2312.16886","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","created":"2023-12-28","cited_by_count":122,"area":"mllm"},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121,"area":"lr"},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120,"area":"lr"},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"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":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2401.09712","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","created":"2024-01-18","cited_by_count":113,"area":"mllm"},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2311.01459","title":"Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization","created":"2023-11-02","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":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99,"area":null},{"id":"2407.12366","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","created":"2024-07-17","cited_by_count":98,"area":"lr"},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96,"area":"mllm"},{"id":"2406.11832","title":"Unveiling Encoder-Free Vision-Language Models","created":"2024-06-17","cited_by_count":94,"area":"mllm"},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2307.12732","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","created":"2023-07-24","cited_by_count":87,"area":"distill"},{"id":"2309.04669","title":"Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization","created":"2023-09-09","cited_by_count":87,"area":"lr"},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86,"area":null},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84,"area":"mllm"},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83,"area":null},{"id":"2312.04265","title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-07","cited_by_count":83,"area":null},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82,"area":"mllm"},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81,"area":null},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81,"area":"mllm"},{"id":"2308.12714","title":"VIGC: Visual Instruction Generation and Correction","created":"2023-08-24","cited_by_count":80,"area":"mllm"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78,"area":null},{"id":"2308.04152","title":"Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions","created":"2023-08-08","cited_by_count":77,"area":"mllm"},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2306.01195","title":"Consistency-guided Prompt Learning for Vision-Language Models","created":"2023-06-01","cited_by_count":73,"area":"mllm"},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2407.08303","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception","created":"2024-07-11","cited_by_count":73,"area":"mllm"},{"id":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null}],"next_cursor":"100"}