{"total":47,"rows":[{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2309.16779","title":"Intriguing properties of generative classifiers","created":"2023-09-28","cited_by_count":52,"area":null},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2308.16777","title":"Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models","created":"2023-08-31","cited_by_count":33,"area":null},{"id":"2410.07160","title":"TextToon: Real-Time Text Toonify Head Avatar from Single Video","created":"2024-09-23","cited_by_count":21,"area":null},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2505.18582","title":"On Denoising Walking Videos for Gait Recognition","created":"2025-05-24","cited_by_count":14,"area":null},{"id":"2502.18176","title":"CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification","created":"2025-02-25","cited_by_count":13,"area":null},{"id":"2403.04321","title":"Discriminative Probing and Tuning for Text-to-Image Generation","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2403.14526","title":"Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2406.02929","title":"ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning","created":"2024-06-05","cited_by_count":10,"area":null},{"id":"2507.04051","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","created":"2025-07-05","cited_by_count":10,"area":null},{"id":"2410.13117","title":"Preference Diffusion for Recommendation","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2512.25034","title":"Generative Classifiers Avoid Shortcut Solutions","created":"2025-12-31","cited_by_count":8,"area":null},{"id":"2404.10718","title":"GazeHTA: End-to-end Gaze Target Detection with Head-Target Association","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2405.09806","title":"A Generalist Model for Diverse Text-Guided Medical Image Synthesis","created":"2024-05-16","cited_by_count":6,"area":null},{"id":"2408.16314","title":"ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2411.15435","title":"What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2307.09233","title":"Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2312.07039","title":"Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2401.13363","title":"Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2408.08982","title":"Deep Generative Classification of Blood Cell Morphology","created":"2024-08-16","cited_by_count":4,"area":null},{"id":"2503.23030","title":"Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning","created":"2025-03-29","cited_by_count":4,"area":null},{"id":"2505.21780","title":"Compositional Scene Understanding through Inverse Generative Modeling","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2603.16641","title":"FlowComposer: Composable Flows for Compositional Zero-Shot Learning","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2311.17072","title":"IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2506.23538","title":"Uncertainty-aware Diffusion and Reinforcement Learning for Joint Plane Localization and Anomaly Diagnosis in 3D Ultrasound","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2510.12060","title":"Your VAR Model is Secretly an Efficient and Explainable Generative Classifier","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2410.03505","title":"Classification-Denoising Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2511.06284","title":"Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2603.14880","title":"RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2610.05684","title":"Two-Sample Testing via Path-based Inference","created":"2026-10-05","cited_by_count":1,"area":null},{"id":"2404.09633","title":"In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2411.11350","title":"Zero and Few Shot Load Forecasting with Large Language Models","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2503.13814","title":"FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classification","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2510.03027","title":"Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.24078","title":"Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2512.09095","title":"Food Image Generation on Multi-Noun Categories","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2602.12401","title":"ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.01361","title":"IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2607.02718","title":"Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.04623","title":"Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.20770","title":"MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2610.03626","title":"Depth as Time in One-Step Generative Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.08277","title":"Two-Sample Testing via Generative Processes","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}