{"total":362,"rows":[{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602,"area":"lr"},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320,"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":"2312.00195","title":"Raising the Bar of AI-generated Image Detection with CLIP","created":"2023-11-30","cited_by_count":164,"area":"mllm"},{"id":"2403.18293","title":"Efficient Test-Time Adaptation of Vision-Language Models","created":"2024-03-27","cited_by_count":141,"area":"mllm"},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123,"area":"mllm"},{"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":"2310.01018","title":"Controlling Vision-Language Models for Multi-Task Image Restoration","created":"2023-10-02","cited_by_count":110,"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":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79,"area":"mllm"},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"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":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70,"area":null},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69,"area":"mllm"},{"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":"2404.02285","title":"LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP","created":"2024-04-02","cited_by_count":60,"area":"mechinterp"},{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59,"area":null},{"id":"2303.08138","title":"Diversity-Aware Meta Visual Prompting","created":"2023-03-14","cited_by_count":58,"area":null},{"id":"2309.07439","title":"DePT: Decoupled Prompt Tuning","created":"2023-09-14","cited_by_count":58,"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":"2211.12739","title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","created":"2022-11-23","cited_by_count":51,"area":"mllm"},{"id":"2307.07397","title":"Improving Zero-Shot Generalization for CLIP with Synthesized Prompts","created":"2023-07-14","cited_by_count":51,"area":"mllm"},{"id":"2305.15316","title":"Training on Thin Air: Improve Image Classification with Generated Data","created":"2023-05-24","cited_by_count":50,"area":"diffusion"},{"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":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2309.16649","title":"FLIP: Cross-domain Face Anti-spoofing with Language Guidance","created":"2023-09-28","cited_by_count":45,"area":null},{"id":"2310.03059","title":"Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models","created":"2023-10-04","cited_by_count":42,"area":null},{"id":"2211.02219","title":"Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models","created":"2022-11-04","cited_by_count":40,"area":"mllm"},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2306.06048","title":"How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?","created":"2023-06-09","cited_by_count":38,"area":"mllm"},{"id":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38,"area":"diffusion"},{"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":"2407.02880","title":"Knowledge Composition using Task Vectors with Learned Anisotropic Scaling","created":"2024-07-03","cited_by_count":37,"area":null},{"id":"2304.04521","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","created":"2023-04-10","cited_by_count":36,"area":null},{"id":"2403.16005","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2406.01837","title":"Boosting Vision-Language Models with Transduction","created":"2024-06-03","cited_by_count":36,"area":"mllm"},{"id":"2407.21794","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey","created":"2024-07-31","cited_by_count":36,"area":"mllm"},{"id":"2211.16191","title":"SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification","created":"2022-11-28","cited_by_count":34,"area":"mllm"},{"id":"2503.12356","title":"Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation","created":"2025-03-16","cited_by_count":33,"area":"diffusion"},{"id":"2401.15422","title":"A Survey on Data Augmentation in Large Model Era","created":"2024-01-27","cited_by_count":31,"area":"diffusion"},{"id":"2407.01400","title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","created":"2024-07-01","cited_by_count":29,"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":"2310.19752","title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP","created":"2023-10-30","cited_by_count":27,"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":"2403.19137","title":"CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models","created":"2024-03-28","cited_by_count":25,"area":"mllm"},{"id":"2304.04512","title":"Defense-Prefix for Preventing Typographic Attacks on CLIP","created":"2023-04-10","cited_by_count":24,"area":"mllm"},{"id":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24,"area":null},{"id":"2310.06311","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","created":"2023-10-10","cited_by_count":24,"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":"2405.11793","title":"MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2409.03868","title":"Few-shot Adaptation of Medical Vision-Language Models","created":"2024-09-05","cited_by_count":24,"area":"mllm"},{"id":"2409.19375","title":"DOTA: Distributional Test-Time Adaptation of Vision-Language Models","created":"2024-09-28","cited_by_count":23,"area":"mllm"},{"id":"2402.19150","title":"Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model","created":"2024-02-29","cited_by_count":22,"area":"mllm"},{"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":"2408.13320","title":"Online Zero-Shot Classification with CLIP","created":"2024-08-23","cited_by_count":22,"area":"mllm"},{"id":"2305.06524","title":"Can SAM Boost Video Super-Resolution?","created":"2023-05-11","cited_by_count":21,"area":null},{"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":"2412.06284","title":"Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data","created":"2024-12-09","cited_by_count":21,"area":null},{"id":"2308.07605","title":"SGDiff: A Style Guided Diffusion Model for Fashion Synthesis","created":"2023-08-15","cited_by_count":20,"area":"diffusion"},{"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":"2308.07539","title":"Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2404.17753","title":"Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification","created":"2024-04-27","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":"2408.14802","title":"RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images","created":"2024-08-27","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":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2304.09042","title":"Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases","created":"2023-04-18","cited_by_count":18,"area":null},{"id":"2311.01734","title":"Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training","created":"2023-11-03","cited_by_count":18,"area":null},{"id":"2407.16977","title":"Selective Vision-Language Subspace Projection for Few-shot CLIP","created":"2024-07-24","cited_by_count":18,"area":"mllm"},{"id":"2401.15914","title":"Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization","created":"2024-01-29","cited_by_count":17,"area":"mllm"},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2311.09191","title":"Domain Aligned CLIP for Few-shot Classification","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2406.20078","title":"GM-DF: Generalized Multi-Scenario Deepfake Detection","created":"2024-06-28","cited_by_count":16,"area":null},{"id":"2509.10555","title":"SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning","created":"2025-09-09","cited_by_count":16,"area":"mllm"},{"id":"2406.11148","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","created":"2024-06-17","cited_by_count":15,"area":"rag"},{"id":"2506.02557","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","created":"2025-06-03","cited_by_count":15,"area":"mllm"},{"id":"2403.04294","title":"A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP","created":"2024-03-07","cited_by_count":14,"area":null},{"id":"2501.03729","title":"Realistic Test-Time Adaptation of Vision-Language Models","created":"2025-01-07","cited_by_count":14,"area":"mllm"},{"id":"2506.17307","title":"Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation","created":"2025-06-18","cited_by_count":14,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2311.17091","title":"Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models","created":"2023-11-28","cited_by_count":13,"area":"mllm"},{"id":"2403.10519","title":"Frozen Feature Augmentation for Few-Shot Image Classification","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2408.10280","title":"NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models","created":"2024-08-18","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":"2301.01156","title":"Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation","created":"2023-01-03","cited_by_count":12,"area":null},{"id":"2306.10191","title":"Neural Priming for Sample-Efficient Adaptation","created":"2023-06-16","cited_by_count":12,"area":null},{"id":"2307.03073","title":"Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning","created":"2023-07-06","cited_by_count":12,"area":"mllm"},{"id":"2307.15460","title":"Cross-Modal Concept Learning and Inference for Vision-Language Models","created":"2023-07-28","cited_by_count":12,"area":"mllm"},{"id":"2503.12866","title":"SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting","created":"2025-03-17","cited_by_count":12,"area":"mllm"},{"id":"2408.05974","title":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","created":"2024-08-12","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":"2505.23271","title":"LADA: Scalable Label-Specific CLIP Adapter for Continual Learning","created":"2025-05-29","cited_by_count":11,"area":"mllm"},{"id":"2303.15234","title":"Prompt Tuning based Adapter for Vision-Language Model Adaption","created":"2023-03-24","cited_by_count":10,"area":"mllm"},{"id":"2304.06957","title":"MVP-SEG: Multi-View Prompt Learning for Open-Vocabulary Semantic Segmentation","created":"2023-04-14","cited_by_count":10,"area":null},{"id":"2305.11092","title":"Universal Domain Adaptation from Foundation Models: A Baseline Study","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2402.06223","title":"Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2405.01468","title":"Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models","created":"2024-05-02","cited_by_count":10,"area":"mllm"}],"next_cursor":"100"}