{"total":321,"rows":[{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585,"area":"diffusion"},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804,"area":null},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647,"area":"mllm"},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563,"area":"mllm"},{"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":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"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":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405,"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":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320,"area":null},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271,"area":null},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"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":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159,"area":"mllm"},{"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":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","cited_by_count":134,"area":null},{"id":"2208.08984","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","created":"2022-08-18","cited_by_count":132,"area":null},{"id":"2302.14042","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","created":"2023-02-27","cited_by_count":128,"area":null},{"id":"2301.13166","title":"ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation","created":"2023-01-30","cited_by_count":127,"area":null},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122,"area":"mllm"},{"id":"2212.04385","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","created":"2022-12-08","cited_by_count":122,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117,"area":null},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"area":null},{"id":"2203.07190","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","created":"2022-03-14","cited_by_count":113,"area":null},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109,"area":"mllm"},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2308.15126","title":"Evaluation and Analysis of Hallucination in Large Vision-Language Models","created":"2023-08-29","cited_by_count":99,"area":"mllm"},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86,"area":null},{"id":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85,"area":null},{"id":"2112.13906","title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","created":"2021-12-27","cited_by_count":85,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2203.15685","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","created":"2022-03-29","cited_by_count":83,"area":null},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79,"area":null},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72,"area":null},{"id":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72,"area":"mllm"},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71,"area":null},{"id":"2203.06386","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","created":"2022-03-12","cited_by_count":70,"area":"mllm"},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70,"area":"mllm"},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70,"area":"mllm"},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69,"area":null},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67,"area":null},{"id":"2407.04842","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","created":"2024-07-05","cited_by_count":66,"area":"diffusion"},{"id":"2303.17811","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","created":"2023-03-31","cited_by_count":61,"area":null},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60,"area":null},{"id":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60,"area":"offlinerl"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2308.14960","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","created":"2023-08-29","cited_by_count":58,"area":"mllm"},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55,"area":"distill"},{"id":"2211.16649","title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation","created":"2022-11-30","cited_by_count":55,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2303.05952","title":"Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning","created":"2023-03-10","cited_by_count":53,"area":null},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53,"area":null},{"id":"2210.09292","title":"Efficient Diffusion Models for Vision: A Survey","created":"2022-10-07","cited_by_count":51,"area":"diffusion"},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51,"area":"mllm"},{"id":"2404.10241","title":"Vision-and-Language Navigation via Causal Learning","created":"2024-04-16","cited_by_count":51,"area":null},{"id":"2202.02317","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","created":"2022-02-04","cited_by_count":45,"area":null},{"id":"2205.15509","title":"ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts","created":"2022-05-31","cited_by_count":45,"area":null},{"id":"2501.00569","title":"Probing Visual Language Priors in VLMs","created":"2024-12-31","cited_by_count":45,"area":"lr"},{"id":"2307.12335","title":"Learning Navigational Visual Representations with Semantic Map Supervision","created":"2023-07-23","cited_by_count":43,"area":null},{"id":"2302.00275","title":"Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization","created":"2023-02-01","cited_by_count":41,"area":null},{"id":"2207.13162","title":"Retrieval-Augmented Transformer for Image Captioning","created":"2022-07-26","cited_by_count":38,"area":"rag"},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2304.07919","title":"Chain of Thought Prompt Tuning in Vision Language Models","created":"2023-04-16","cited_by_count":34,"area":"lr"},{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34,"area":"mllm"},{"id":"2407.05342","title":"Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models","created":"2024-07-07","cited_by_count":34,"area":"mllm"},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2303.12793","title":"CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning","created":"2023-03-22","cited_by_count":33,"area":null},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33,"area":"mllm"},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2307.01981","title":"A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosis","created":"2023-07-05","cited_by_count":31,"area":null},{"id":"2207.00422","title":"Personalized Showcases: Generating Multi-Modal Explanations for Recommendations","created":"2022-06-30","cited_by_count":30,"area":null},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"}],"next_cursor":"100"}