{"total":1173,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181,"area":"diffusion"},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972,"area":"diffusion"},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909,"area":"mllm"},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"area":"mllm"},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"area":null},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535,"area":"diffusion"},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531,"area":"wm"},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520,"area":null},{"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":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336,"area":null},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329,"area":"mllm"},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306,"area":"diffusion"},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270,"area":null},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247,"area":"diffusion"},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"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":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219,"area":null},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218,"area":"mllm"},{"id":"2305.20030","title":"Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust","created":"2023-05-31","cited_by_count":187,"area":"diffusion"},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169,"area":null},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165,"area":"mllm"},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155,"area":null},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150,"area":"wm"},{"id":"2404.04956","title":"Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models","created":"2024-04-07","cited_by_count":142,"area":"diffusion"},{"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":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"area":null},{"id":"2305.17382","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","created":"2023-05-27","cited_by_count":130,"area":null},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129,"area":null},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129,"area":null},{"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":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"area":"mllm"},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120,"area":"lr"},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"area":"mllm"},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","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":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"area":null},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109,"area":null},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"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":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99,"area":null},{"id":"2311.15537","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","created":"2023-11-27","cited_by_count":97,"area":null},{"id":"2502.03444","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","created":"2025-02-05","cited_by_count":96,"area":"diffusion"},{"id":"2407.21720","title":"Detecting, Explaining, and Mitigating Memorization in Diffusion Models","created":"2024-07-31","cited_by_count":95,"area":"diffusion"},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2312.00878","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers","created":"2023-12-01","cited_by_count":91,"area":"mllm"},{"id":"2404.14055","title":"RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2401.01970","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","created":"2024-01-03","cited_by_count":86,"area":null},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83,"area":"mllm"},{"id":"2405.19092","title":"Benchmarking and Improving Detail Image Caption","created":"2024-05-29","cited_by_count":81,"area":null},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79,"area":"mllm"},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2412.16334","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","created":"2024-12-20","cited_by_count":79,"area":null},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77,"area":"mllm"},{"id":"2304.13013","title":"Stable and low-precision training for large-scale vision-language models","created":"2023-04-25","cited_by_count":75,"area":"mllm"},{"id":"2503.21979","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","created":"2025-03-27","cited_by_count":74,"area":null},{"id":"2504.17432","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","created":"2025-04-24","cited_by_count":73,"area":"mllm"},{"id":"2509.01563","title":"Kwai Keye-VL 1.5 Technical Report","created":"2025-09-01","cited_by_count":73,"area":"mllm"},{"id":"2312.06960","title":"Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment","created":"2023-12-12","cited_by_count":71,"area":"mllm"},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70,"area":null},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70,"area":"mllm"},{"id":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69,"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":"2311.16194","title":"BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP","created":"2023-11-26","cited_by_count":67,"area":"mllm"},{"id":"2403.13043","title":"When Do We Not Need Larger Vision Models?","created":"2024-03-19","cited_by_count":67,"area":null},{"id":"2304.13023","title":"Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images","created":"2023-04-25","cited_by_count":66,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2407.02158","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","created":"2024-07-02","cited_by_count":65,"area":null},{"id":"2401.12425","title":"The Neglected Tails in Vision-Language Models","created":"2024-01-23","cited_by_count":63,"area":"mllm"},{"id":"2501.01320","title":"SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration","created":"2025-01-02","cited_by_count":62,"area":"diffusion"},{"id":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2501.14729","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","created":"2025-01-24","cited_by_count":56,"area":"wm"},{"id":"2406.14596","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","created":"2024-06-20","cited_by_count":55,"area":"lr"},{"id":"2501.05952","title":"Scalable Vision Language Model Training via High Quality Data Curation","created":"2025-01-10","cited_by_count":55,"area":"mllm"},{"id":"2503.04812","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","created":"2025-03-04","cited_by_count":55,"area":null},{"id":"2403.13438","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","created":"2024-03-18","cited_by_count":54,"area":"lr"}],"next_cursor":"100"}