{"total":267,"rows":[{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"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":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336,"area":"mllm"},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"area":null},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187,"area":null},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128,"area":"vla"},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119,"area":"mllm"},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101,"area":"mllm"},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"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":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2302.03298","title":"Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion","created":"2023-02-07","cited_by_count":81,"area":"diffusion"},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"area":null},{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73,"area":"mllm"},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2403.06659","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","created":"2024-03-11","cited_by_count":67,"area":null},{"id":"2405.02266","title":"On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?","created":"2024-05-03","cited_by_count":67,"area":"mllm"},{"id":"2401.12425","title":"The Neglected Tails in Vision-Language Models","created":"2024-01-23","cited_by_count":63,"area":"mllm"},{"id":"2401.02460","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","created":"2024-01-04","cited_by_count":54,"area":"mllm"},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53,"area":null},{"id":"2403.17589","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","created":"2024-03-26","cited_by_count":52,"area":"mllm"},{"id":"2307.11661","title":"Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts","created":"2023-07-21","cited_by_count":50,"area":"mllm"},{"id":"2305.18287","title":"LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections","created":"2023-05-29","cited_by_count":43,"area":null},{"id":"2312.10908","title":"CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update","created":"2023-12-18","cited_by_count":43,"area":null},{"id":"2311.16241","title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","created":"2023-11-27","cited_by_count":41,"area":null},{"id":"2311.16494","title":"ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models","created":"2023-11-27","cited_by_count":39,"area":"mllm"},{"id":"2401.02418","title":"Learning to Prompt with Text Only Supervision for Vision-Language Models","created":"2024-01-04","cited_by_count":38,"area":"mllm"},{"id":"2410.12790","title":"Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models","created":"2024-10-16","cited_by_count":38,"area":"mllm"},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36,"area":null},{"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":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35,"area":"mllm"},{"id":"2312.09788","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-15","cited_by_count":34,"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":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33,"area":"mllm"},{"id":"2406.02915","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","created":"2024-06-05","cited_by_count":30,"area":"mllm"},{"id":"2309.00096","title":"AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation","created":"2023-08-31","cited_by_count":29,"area":null},{"id":"2403.11755","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","created":"2024-03-18","cited_by_count":29,"area":"mllm"},{"id":"2211.15603","title":"Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation","created":"2022-11-28","cited_by_count":28,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2404.04072","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","created":"2024-04-05","cited_by_count":28,"area":"mllm"},{"id":"2407.04603","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","created":"2024-07-05","cited_by_count":28,"area":"mllm"},{"id":"2410.19294","title":"Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting","created":"2024-10-25","cited_by_count":26,"area":"mllm"},{"id":"2311.11178","title":"Active Prompt Learning in Vision Language Models","created":"2023-11-18","cited_by_count":25,"area":"mllm"},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25,"area":null},{"id":"2403.19137","title":"CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models","created":"2024-03-28","cited_by_count":25,"area":"mllm"},{"id":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24,"area":"mllm"},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2409.19375","title":"DOTA: Distributional Test-Time Adaptation of Vision-Language Models","created":"2024-09-28","cited_by_count":23,"area":"mllm"},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","cited_by_count":20,"area":"mllm"},{"id":"2404.17753","title":"Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification","created":"2024-04-27","cited_by_count":19,"area":null},{"id":"2407.11335","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","created":"2024-07-16","cited_by_count":19,"area":"mllm"},{"id":"2410.15430","title":"BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping","created":"2024-10-20","cited_by_count":19,"area":"mllm"},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2308.01313","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","created":"2023-08-02","cited_by_count":17,"area":"mllm"},{"id":"2312.00096","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","created":"2023-11-30","cited_by_count":16,"area":"mllm"},{"id":"2404.12652","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","created":"2024-04-19","cited_by_count":16,"area":"mllm"},{"id":"2410.15364","title":"Scene Graph Generation with Role-Playing Large Language Models","created":"2024-10-20","cited_by_count":16,"area":"mllm"},{"id":"2510.24038","title":"Enhancing CLIP Robustness via Cross-Modality Alignment","created":"2025-10-28","cited_by_count":15,"area":"mllm"},{"id":"2310.09929","title":"Prompting Scientific Names for Zero-Shot Species Recognition","created":"2023-10-15","cited_by_count":14,"area":null},{"id":"2311.01064","title":"Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2311.07593","title":"Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification","created":"2023-11-10","cited_by_count":13,"area":"mllm"},{"id":"2401.04651","title":"Learning to Prompt Segment Anything Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2502.19844","title":"ProAPO: Progressively Automatic Prompt Optimization for Visual Classification","created":"2025-02-27","cited_by_count":13,"area":"mllm"},{"id":"2507.03657","title":"Dynamic Multimodal Prototype Learning in Vision-Language Models","created":"2025-07-04","cited_by_count":13,"area":"mllm"},{"id":"2306.10191","title":"Neural Priming for Sample-Efficient Adaptation","created":"2023-06-16","cited_by_count":12,"area":null},{"id":"2308.09033","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2311.11904","title":"LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions","created":"2023-11-20","cited_by_count":11,"area":"mllm"},{"id":"2311.18402","title":"MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2405.10053","title":"SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2405.14977","title":"A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models","created":"2024-05-23","cited_by_count":11,"area":"mllm"},{"id":"2405.01468","title":"Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models","created":"2024-05-02","cited_by_count":10,"area":"mllm"},{"id":"2405.15668","title":"What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models","created":"2024-05-24","cited_by_count":10,"area":"mllm"},{"id":"2410.01544","title":"Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2503.18623","title":"Training-Free Personalization via Retrieval and Reasoning on Fingerprints","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2511.05681","title":"Culture in Action: Evaluating Text-to-Image Models through Social Activities","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2403.02626","title":"Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2405.08992","title":"Contextual Emotion Recognition using Large Vision Language Models","created":"2024-05-14","cited_by_count":9,"area":"mllm"},{"id":"2412.09402","title":"MultiEYE: Dataset and Benchmark for OCT-Enhanced Retinal Disease Recognition from Fundus Images","created":"2024-12-12","cited_by_count":9,"area":null},{"id":"2302.12948","title":"Agile Modeling: From Concept to Classifier in Minutes","created":"2023-02-25","cited_by_count":8,"area":null},{"id":"2309.06809","title":"TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2403.12964","title":"Enhancing Vision-Language Few-Shot Adaptation with Negative Learning","created":"2024-03-19","cited_by_count":8,"area":"mllm"},{"id":"2404.00701","title":"Training-Free Semantic Segmentation via LLM-Supervision","created":"2024-03-31","cited_by_count":8,"area":null},{"id":"2408.00759","title":"Text-Guided Video Masked Autoencoder","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2408.06970","title":"Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2412.18303","title":"Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model","created":"2024-12-24","cited_by_count":8,"area":"mllm"},{"id":"2501.13982","title":"Attribute-based Visual Reprogramming for Vision-Language Models","created":"2025-01-23","cited_by_count":8,"area":"mllm"},{"id":"2508.03207","title":"Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration","created":"2025-08-05","cited_by_count":8,"area":null},{"id":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2311.17315","title":"Explaining CLIP's performance disparities on data from blind/low vision users","created":"2023-11-29","cited_by_count":7,"area":"mllm"}],"next_cursor":"100"}