{"total":1274,"rows":[{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355,"area":"diffusion"},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152,"area":null},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581,"area":"wm"},{"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":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080,"area":null},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114,"area":"diffusion"},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"area":null},{"id":"2210.10163","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","created":"2022-10-18","cited_by_count":570,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531,"area":"wm"},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511,"area":null},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455,"area":"mllm"},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"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":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388,"area":"mllm"},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388,"area":"lr"},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"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":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316,"area":"mllm"},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300,"area":"mllm"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"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":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267,"area":null},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260,"area":"mllm"},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254,"area":"lr"},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2410.23262","title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","created":"2024-10-30","cited_by_count":231,"area":"driving"},{"id":"2410.05160","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","created":"2024-10-07","cited_by_count":228,"area":"mllm"},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222,"area":"lr"},{"id":"2210.02928","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","created":"2022-10-06","cited_by_count":220,"area":"rag"},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217,"area":null},{"id":"2301.04558","title":"Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing","created":"2023-01-11","cited_by_count":211,"area":null},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209,"area":"moe"},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203,"area":"moe"},{"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":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201,"area":null},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198,"area":null},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197,"area":"mllm"},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2303.07338","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need","created":"2023-03-13","cited_by_count":184,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176,"area":null},{"id":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165,"area":null},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164,"area":null},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156,"area":null},{"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":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151,"area":"mllm"},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149,"area":null},{"id":"2310.18660","title":"Foundation Models for Generalist Geospatial Artificial Intelligence","created":"2023-10-28","cited_by_count":149,"area":null},{"id":"2312.14115","title":"LingoQA: Visual Question Answering for Autonomous Driving","created":"2023-12-21","cited_by_count":145,"area":"mllm"},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2306.07831","title":"Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images","created":"2023-06-13","cited_by_count":134,"area":null},{"id":"2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","created":"2025-01-09","cited_by_count":134,"area":"lr"},{"id":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123,"area":"mllm"},{"id":"2207.07039","title":"Convolutional Bypasses Are Better Vision Transformer Adapters","created":"2022-07-14","cited_by_count":121,"area":null},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null}],"next_cursor":"100"}