{"total":75,"rows":[{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346,"area":"wm"},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199,"area":null},{"id":"2306.13090","title":"PromptIR: Prompting for All-in-One Blind Image Restoration","created":"2023-06-22","cited_by_count":114,"area":null},{"id":"2211.11635","title":"Understanding and Improving Visual Prompting: A Label-Mapping Perspective","created":"2022-11-21","cited_by_count":87,"area":null},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83,"area":"diffusion"},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77,"area":"mllm"},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2409.01083","title":"Affordance-based Robot Manipulation with Flow Matching","created":"2024-09-02","cited_by_count":54,"area":"diffusion"},{"id":"2407.07520","title":"IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection","created":"2024-07-10","cited_by_count":46,"area":null},{"id":"2312.05447","title":"From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos","created":"2023-12-09","cited_by_count":39,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"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":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31,"area":null},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30,"area":null},{"id":"2309.01155","title":"LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models","created":"2023-09-03","cited_by_count":29,"area":"mllm"},{"id":"2310.08381","title":"AutoVP: An Automated Visual Prompting Framework and Benchmark","created":"2023-10-12","cited_by_count":29,"area":null},{"id":"2309.13847","title":"Tuning Multi-mode Token-level Prompt Alignment across Modalities","created":"2023-09-25","cited_by_count":26,"area":"mllm"},{"id":"2305.11577","title":"LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model","created":"2023-05-19","cited_by_count":25,"area":"diffusion"},{"id":"2312.00360","title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24,"area":null},{"id":"2403.18920","title":"CPR: Retrieval Augmented Generation for Copyright Protection","created":"2024-03-27","cited_by_count":24,"area":"rag"},{"id":"2402.02242","title":"Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark","created":"2024-02-03","cited_by_count":23,"area":null},{"id":"2510.13219","title":"Prompt-based Adaptation in Large-scale Vision Models: A Survey","created":"2025-10-15","cited_by_count":21,"area":null},{"id":"2404.17433","title":"PromptCIR: Blind Compressed Image Restoration with Prompt Learning","created":"2024-04-26","cited_by_count":20,"area":null},{"id":"2307.14397","title":"A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot","created":"2023-07-26","cited_by_count":19,"area":null},{"id":"2405.17898","title":"FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2308.01937","title":"Training Data Protection with Compositional Diffusion Models","created":"2023-08-02","cited_by_count":17,"area":"diffusion"},{"id":"2301.12171","title":"ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts","created":"2023-01-28","cited_by_count":16,"area":null},{"id":"2310.01260","title":"SPELL: Semantic Prompt Evolution based on a LLM","created":"2023-10-02","cited_by_count":15,"area":null},{"id":"2507.21160","title":"Handling Out-of-Distribution Data: A Survey","created":"2025-07-25","cited_by_count":14,"area":null},{"id":"2310.02663","title":"MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translation","created":"2023-10-04","cited_by_count":13,"area":null},{"id":"2403.00269","title":"Large Convolutional Model Tuning via Filter Subspace","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2306.00763","title":"Learning Disentangled Prompts for Compositional Image Synthesis","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2401.09716","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","created":"2024-01-18","cited_by_count":8,"area":null},{"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":"2403.16497","title":"PathoTune: Adapting Visual Foundation Model to Pathological Specialists","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2407.13108","title":"UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2507.15905","title":"Foundation Models and Transformers for Anomaly Detection: A Survey","created":"2025-07-21","cited_by_count":8,"area":null},{"id":"2406.19341","title":"Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptation","created":"2024-06-27","cited_by_count":7,"area":null},{"id":"2410.18615","title":"FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2307.05707","title":"MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2501.18936","title":"Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts","created":"2025-01-31","cited_by_count":5,"area":"moe"},{"id":"2505.18423","title":"CENet: Context Enhancement Network for Medical Image Segmentation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2303.04998","title":"Rethinking Visual Prompt Learning as Masked Visual Token Modeling","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2405.15161","title":"Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2408.13983","title":"Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation","created":"2024-08-26","cited_by_count":4,"area":null},{"id":"2503.20282","title":"Faster Parameter-Efficient Tuning with Token Redundancy Reduction","created":"2025-03-26","cited_by_count":4,"area":"inference"},{"id":"2506.02843","title":"Random Registers for Cross-Domain Few-Shot Learning","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2211.16299","title":"Transferability Estimation Based On Principal Gradient Expectation","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2401.06374","title":"SamLP: A Customized Segment Anything Model for License Plate Detection","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2405.13951","title":"Text Prompting for Multi-Concept Video Customization by Autoregressive Generation","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2405.17877","title":"Sparsity- and Hybridity-Inspired Visual Parameter-Efficient Fine-Tuning for Medical Diagnosis","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2407.11902","title":"Encapsulating Knowledge in One Prompt","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","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":"2311.10339","title":"A2XP: Towards Private Domain Generalization","created":"2023-11-17","cited_by_count":2,"area":null},{"id":"2401.10962","title":"One Step Learning, One Step Review","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2403.11537","title":"Semantic Prompting with Image-Token for Continual Learning","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2409.16491","title":"Proactive Schemes: A Survey of Adversarial Attacks for Social Good","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2411.15276","title":"Event USKT : U-State Space Model in Knowledge Transfer for Event Cameras","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2503.06084","title":"Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2503.18337","title":"Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2601.20232","title":"Visual Prompt-Agnostic Evolution","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.10502","title":"Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2310.16062","title":"Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2403.18193","title":"Middle Fusion and Multi-Stage, Multi-Form Prompts for Robust RGB-T Tracking","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2503.06200","title":"Removing Multiple Hybrid Adverse Weather in Video via a Unified Model","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2503.21820","title":"UFM: Unified Feature Matching Pre-training with Multi-Modal Image Assistants","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2405.14857","title":"Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations","created":"2024-05-23","cited_by_count":0,"area":"diffusion"},{"id":"2408.10383","title":"BrewCLIP: A Bifurcated Representation Learning Framework for Audio-Visual Retrieval","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2505.09123","title":"Promoting SAM for Camouflaged Object Detection via Selective Key Point-based Guidance","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2512.12673","title":"Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2604.22838","title":"Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.19944","title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.14595","title":"MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation","created":"2026-07-16","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}