{"total":317,"rows":[{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"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":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798,"area":null},{"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":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482,"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":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"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":"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":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302,"area":null},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229,"area":null},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217,"area":null},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205,"area":"diffusion"},{"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":"2306.09305","title":"Fast Training of Diffusion Models with Masked Transformers","created":"2023-06-15","cited_by_count":176,"area":"diffusion"},{"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":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164,"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":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"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":"2306.09347","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","created":"2023-06-15","cited_by_count":125,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"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":"2302.00861","title":"SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling","created":"2023-02-02","cited_by_count":115,"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":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"area":null},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"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":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99,"area":null},{"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":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","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":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84,"area":null},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82,"area":"mllm"},{"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":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"id":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77,"area":null},{"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":"2401.02955","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","created":"2024-01-05","cited_by_count":75,"area":null},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"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":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69,"area":null},{"id":"2402.13232","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","created":"2024-02-20","cited_by_count":69,"area":null},{"id":"2406.04292","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53,"area":"mllm"},{"id":"2307.12914","title":"Towards a Visual-Language Foundation Model for Computational Pathology","created":"2023-07-24","cited_by_count":52,"area":null},{"id":"2405.11618","title":"Transcriptomics-guided Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":51,"area":null},{"id":"2403.17004","title":"SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer","created":"2024-03-25","cited_by_count":49,"area":"diffusion"},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48,"area":null},{"id":"2306.04811","title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","created":"2023-06-07","cited_by_count":47,"area":"mllm"},{"id":"2308.13382","title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","created":"2023-08-25","cited_by_count":44,"area":null},{"id":"2402.09611","title":"Towards Privacy-Aware Sign Language Translation at Scale","created":"2024-02-14","cited_by_count":44,"area":null},{"id":"2307.08347","title":"M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization","created":"2023-07-17","cited_by_count":43,"area":"mllm"},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43,"area":null},{"id":"2405.00740","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","created":"2024-04-30","cited_by_count":42,"area":"mllm"},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2510.05014","title":"Think Then Embed: Generative Context Improves Multimodal Embedding","created":"2025-10-06","cited_by_count":41,"area":"lr"},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2306.06354","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","created":"2023-06-10","cited_by_count":36,"area":"mllm"},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36,"area":"mllm"},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2410.23132","title":"Revisiting MAE pre-training for 3D medical image segmentation","created":"2024-10-30","cited_by_count":35,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2410.16162","title":"Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning","created":"2024-10-21","cited_by_count":34,"area":"lr"},{"id":"2401.04727","title":"Revisiting Adversarial Training at Scale","created":"2024-01-09","cited_by_count":33,"area":null},{"id":"2505.04410","title":"DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception","created":"2025-05-07","cited_by_count":33,"area":null},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32,"area":null},{"id":"2309.00775","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","created":"2023-09-02","cited_by_count":31,"area":null},{"id":"2312.09128","title":"Tokenize Anything via Prompting","created":"2023-12-14","cited_by_count":31,"area":null},{"id":"2403.07369","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","created":"2024-03-12","cited_by_count":31,"area":null},{"id":"2407.03475","title":"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks","created":"2024-07-03","cited_by_count":31,"area":"distill"},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2306.04272","title":"On the Generalization of Multi-modal Contrastive Learning","created":"2023-06-07","cited_by_count":30,"area":null},{"id":"2403.07839","title":"MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2501.02430","title":"FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance","created":"2025-01-05","cited_by_count":30,"area":"mllm"},{"id":"2504.10462","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","created":"2025-04-14","cited_by_count":30,"area":"mllm"},{"id":"2307.05314","title":"Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering","created":"2023-07-11","cited_by_count":29,"area":null},{"id":"2401.14391","title":"Rethinking Patch Dependence for Masked Autoencoders","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28,"area":"mllm"},{"id":"2408.02859","title":"Multistain Pretraining for Slide Representation Learning in Pathology","created":"2024-08-05","cited_by_count":28,"area":null},{"id":"2410.08021","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2502.08391","title":"ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification","created":"2025-02-12","cited_by_count":28,"area":null},{"id":"2507.13575","title":"Apple Intelligence Foundation Language Models: Tech Report 2025","created":"2025-07-17","cited_by_count":28,"area":"moe"},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2402.19326","title":"Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction","created":"2024-02-29","cited_by_count":27,"area":null},{"id":"2410.05249","title":"LoTLIP: Improving Language-Image Pre-training for Long Text Understanding","created":"2024-10-07","cited_by_count":27,"area":null},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2410.01768","title":"SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images","created":"2024-10-02","cited_by_count":25,"area":null},{"id":"2306.15658","title":"CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a \\$10,000 Budget; An Extra \\$4,000 Unlocks 81.8% Accuracy","created":"2023-06-27","cited_by_count":24,"area":null},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null}],"next_cursor":"100"}