{"total":103,"rows":[{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"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":"2212.06785","title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","created":"2022-12-13","cited_by_count":144,"area":null},{"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":"2405.18541","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":104,"area":"mllm"},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99,"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":"2303.16894","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","created":"2023-03-29","cited_by_count":70,"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":"2303.08129","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2402.04087","title":"A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation","created":"2024-02-06","cited_by_count":53,"area":null},{"id":"2302.14007","title":"Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training","created":"2023-02-27","cited_by_count":52,"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":"2312.09553","title":"Prompt-based Distribution Alignment for Unsupervised Domain Adaptation","created":"2023-12-15","cited_by_count":44,"area":"mllm"},{"id":"2411.09219","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","created":"2024-11-14","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2406.01837","title":"Boosting Vision-Language Models with Transduction","created":"2024-06-03","cited_by_count":36,"area":"mllm"},{"id":"2303.08134","title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","created":"2023-03-14","cited_by_count":34,"area":null},{"id":"2412.10817","title":"Enhance Vision-Language Alignment with Noise","created":"2024-12-14","cited_by_count":34,"area":null},{"id":"2403.12952","title":"Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models","created":"2024-03-19","cited_by_count":32,"area":"mllm"},{"id":"2503.10080","title":"Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection","created":"2025-03-13","cited_by_count":31,"area":"mllm"},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"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":"2312.10692","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","created":"2023-12-17","cited_by_count":24,"area":null},{"id":"2410.21802","title":"Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models","created":"2024-10-29","cited_by_count":23,"area":"mllm"},{"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":"2404.08958","title":"AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning","created":"2024-04-13","cited_by_count":22,"area":"mllm"},{"id":"2311.14064","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","created":"2023-11-23","cited_by_count":21,"area":"mllm"},{"id":"2405.08458","title":"Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation","created":"2024-05-14","cited_by_count":20,"area":null},{"id":"2312.14465","title":"FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection","created":"2023-12-22","cited_by_count":19,"area":null},{"id":"2404.01751","title":"T-VSL: Text-Guided Visual Sound Source Localization in Mixtures","created":"2024-04-02","cited_by_count":19,"area":null},{"id":"2408.03120","title":"Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baseline","created":"2024-08-06","cited_by_count":19,"area":null},{"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":"2407.15913","title":"Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models","created":"2024-07-22","cited_by_count":17,"area":"mllm"},{"id":"2311.09191","title":"Domain Aligned CLIP for Few-shot Classification","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2407.01029","title":"EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting","created":"2024-07-01","cited_by_count":16,"area":null},{"id":"2305.00109","title":"Zero-shot performance of the Segment Anything Model (SAM) in 2D medical imaging: A comprehensive evaluation and practical guidelines","created":"2023-04-28","cited_by_count":15,"area":null},{"id":"2409.04796","title":"Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection","created":"2024-09-07","cited_by_count":15,"area":null},{"id":"2501.11175","title":"ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models","created":"2025-01-19","cited_by_count":15,"area":"mllm"},{"id":"2405.00754","title":"CLIPArTT: Adaptation of CLIP to New Domains at Test Time","created":"2024-05-01","cited_by_count":14,"area":"mllm"},{"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":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2403.02649","title":"Few-shot Learner Parameterization by Diffusion Time-steps","created":"2024-03-05","cited_by_count":11,"area":null},{"id":"2504.12104","title":"Logits DeConfusion with CLIP for Few-Shot Learning","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2212.05404","title":"Cap2Aug: Caption guided Image to Image data Augmentation","created":"2022-12-11","cited_by_count":10,"area":"diffusion"},{"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":"2403.01209","title":"Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning","created":"2024-03-02","cited_by_count":8,"area":"mllm"},{"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":"2307.15049","title":"Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models","created":"2023-07-27","cited_by_count":7,"area":"mllm"},{"id":"2503.21775","title":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2506.18504","title":"Generalizing vision-language models to novel domains: A comprehensive survey","created":"2025-06-23","cited_by_count":7,"area":"mllm"},{"id":"2404.00312","title":"Bayesian Exploration of Pre-trained Models for Low-shot Image Classification","created":"2024-03-30","cited_by_count":6,"area":"mllm"},{"id":"2502.06019","title":"Noise is an Efficient Learner for Zero-Shot Vision-Language Models","created":"2025-02-09","cited_by_count":6,"area":"mllm"},{"id":"2503.15337","title":"Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2506.03117","title":"Targeted Forgetting of Image Subgroups in CLIP Models","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2602.00522","title":"MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval","created":"2026-01-31","cited_by_count":6,"area":"mllm"},{"id":"2311.11293","title":"From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2408.04879","title":"On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2507.14312","title":"CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation","created":"2025-07-18","cited_by_count":5,"area":"mllm"},{"id":"2510.21122","title":"NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2306.04715","title":"UniBoost: Unsupervised Unimodal Pre-training for Boosting Zero-shot Vision-Language Tasks","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2409.15077","title":"TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2308.15273","title":"Cross-Modal Retrieval Meets Inference:Improving Zero-Shot Classification with Cross-Modal Retrieval","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2403.02714","title":"DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2405.12710","title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2410.08895","title":"Calibrated Cache Model for Few-Shot Vision-Language Model Adaptation","created":"2024-10-11","cited_by_count":3,"area":"mllm"},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2503.19145","title":"Compositional Caching for Training-free Open-vocabulary Attribute Detection","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2512.11458","title":"Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation","created":"2025-12-12","cited_by_count":3,"area":null},{"id":"2601.00623","title":"DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations","created":"2026-01-02","cited_by_count":3,"area":"mllm"},{"id":"2606.14299","title":"What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective","created":"2026-06-12","cited_by_count":3,"area":"mllm"},{"id":"2406.11309","title":"BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models","created":"2024-06-17","cited_by_count":2,"area":"mllm"},{"id":"2409.11338","title":"CLIP Adaptation by Intra-modal Overlap Reduction","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2510.26466","title":"Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition","created":"2025-10-30","cited_by_count":2,"area":"mllm"},{"id":"2301.03127","title":"Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder Architecture","created":"2023-01-09","cited_by_count":1,"area":null},{"id":"2404.09778","title":"The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2408.09706","title":"MePT: Multi-Representation Guided Prompt Tuning for Vision-Language Model","created":"2024-08-19","cited_by_count":1,"area":"mllm"},{"id":"2410.09365","title":"Debiasing Vison-Language Models with Text-Only Training","created":"2024-10-12","cited_by_count":1,"area":"mllm"},{"id":"2410.11686","title":"A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem","created":"2024-10-15","cited_by_count":1,"area":"mllm"},{"id":"2412.00139","title":"EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2412.15813","title":"Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2412.17601","title":"AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2507.10355","title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","created":"2025-07-14","cited_by_count":1,"area":"mllm"},{"id":"2508.04136","title":"UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval","created":"2025-08-06","cited_by_count":1,"area":"mllm"},{"id":"2512.11941","title":"DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2603.05053","title":"CLIP-driven Zero-shot Learning with Ambiguous Labels","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.09921","title":"WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.24181","title":"Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection","created":"2026-03-25","cited_by_count":1,"area":"mllm"},{"id":"2404.10357","title":"Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models","created":"2024-04-16","cited_by_count":0,"area":"mllm"},{"id":"2406.05432","title":"Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models","created":"2024-06-08","cited_by_count":0,"area":"mllm"},{"id":"2411.06071","title":"GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection","created":"2024-11-09","cited_by_count":0,"area":null},{"id":"2507.03458","title":"Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach","created":"2025-07-04","cited_by_count":0,"area":"mllm"},{"id":"2508.04028","title":"Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval","created":"2025-08-06","cited_by_count":0,"area":"mllm"},{"id":"2508.12861","title":"Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models","created":"2025-08-18","cited_by_count":0,"area":"mllm"},{"id":"2508.12877","title":"Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning","created":"2025-08-18","cited_by_count":0,"area":"mllm"},{"id":"2512.17160","title":"Can Synthetic Images Serve as Effective and Efficient Class Prototypes?","created":"2025-12-19","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}