{"total":71,"rows":[{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"area":null},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83,"area":"mllm"},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2402.07087","title":"Self-Correcting Self-Consuming Loops for Generative Model Training","created":"2024-02-11","cited_by_count":37,"area":null},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2601.05573","title":"Orient Anything V2: Unifying Orientation and Rotation Understanding","created":"2026-01-09","cited_by_count":23,"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":"2410.07838","title":"Minority-Focused Text-to-Image Generation via Prompt Optimization","created":"2024-10-10","cited_by_count":18,"area":"diffusion"},{"id":"2410.10817","title":"When Does Perceptual Alignment Benefit Vision Representations?","created":"2024-10-14","cited_by_count":18,"area":null},{"id":"2411.05561","title":"Objective drives the consistency of representational similarity across datasets","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2502.15588","title":"Improving the Scaling Laws of Synthetic Data with Deliberate Practice","created":"2025-02-21","cited_by_count":17,"area":null},{"id":"2412.01876","title":"Understanding Bias in Large-Scale Visual Datasets","created":"2024-12-02","cited_by_count":15,"area":null},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2411.13842","title":"Detecting Human Artifacts from Text-to-Image Models","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2407.10366","title":"Accessing Vision Foundation Models via ImageNet-1K","created":"2024-07-15","cited_by_count":10,"area":null},{"id":"2409.05162","title":"Can OOD Object Detectors Learn from Foundation Models?","created":"2024-09-08","cited_by_count":10,"area":null},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2410.13523","title":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","created":"2024-10-17","cited_by_count":7,"area":"mllm"},{"id":"2502.03081","title":"Human-Aligned Image Models Improve Visual Decoding from the Brain","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2508.11317","title":"Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models","created":"2025-08-15","cited_by_count":7,"area":"mllm"},{"id":"2508.12026","title":"Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems","created":"2025-08-16","cited_by_count":7,"area":"lr"},{"id":"2401.10744","title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","created":"2024-01-19","cited_by_count":6,"area":"lr"},{"id":"2602.19946","title":"When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators","created":"2026-02-23","cited_by_count":6,"area":"diffusion"},{"id":"2405.18029","title":"Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?","created":"2024-05-28","cited_by_count":5,"area":"diffusion"},{"id":"2503.21449","title":"Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving","created":"2025-03-27","cited_by_count":5,"area":"wm"},{"id":"2403.13804","title":"Learning from Synthetic Data for Visual Grounding","created":"2024-03-20","cited_by_count":4,"area":"synth"},{"id":"2403.18334","title":"DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2405.13779","title":"Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2406.20085","title":"Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language","created":"2024-06-28","cited_by_count":4,"area":"diffusion"},{"id":"2503.17856","title":"ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling","created":"2025-03-22","cited_by_count":4,"area":null},{"id":"2504.11457","title":"Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception","created":"2025-04-15","cited_by_count":4,"area":"diffusion"},{"id":"2407.15296","title":"Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2602.07495","title":"Learning Brain Representation with Hierarchical Visual Embeddings","created":"2026-02-07","cited_by_count":3,"area":null},{"id":"2405.16016","title":"ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2407.11664","title":"Mask-guided cross-image attention for zero-shot in-silico histopathologic image generation with a diffusion model","created":"2024-07-16","cited_by_count":2,"area":"diffusion"},{"id":"2412.09115","title":"Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2507.13568","title":"LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2605.18608","title":"Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.00571","title":"On the Difficulty of Learning a Meta-network for Training Data Selection","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2407.03463","title":"Precision at Scale: Domain-Specific Datasets On-Demand","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2412.00684","title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2504.11895","title":"Search is All You Need for Few-shot Anomaly Detection","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2505.11703","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2507.21947","title":"Enhancing Generalization in Data-free Quantization via Mixup-class Prompting","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2508.09550","title":"Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2602.01370","title":"PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles","created":"2026-02-01","cited_by_count":1,"area":"mllm"},{"id":"2602.04328","title":"Multiview Self-Representation Learning across Heterogeneous Views","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.15368","title":"GMAIL: Generative Modality Alignment for generated Image Learning","created":"2026-02-17","cited_by_count":1,"area":"mllm"},{"id":"2605.26353","title":"Personalized Generative Models for Contextual Debiasing","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2404.03256","title":"Multi Positive Contrastive Learning with Pose-Consistent Generated Images","created":"2024-04-04","cited_by_count":0,"area":null},{"id":"2406.04295","title":"Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment","created":"2024-06-06","cited_by_count":0,"area":"diffusion"},{"id":"2409.08884","title":"Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2409.17685","title":"FICAug: Feature-Informed Clustering and Augmentation for Facial-Expression-Based Parkinson's Disease Screening","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2501.09278","title":"Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2501.13718","title":"A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2502.01335","title":"ConceptVAE: Self-Supervised Fine-Grained Concept Disentanglement from 2D Echocardiographies","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2505.22633","title":"Spatial Knowledge Graph-Guided Multimodal Synthesis","created":"2025-05-28","cited_by_count":0,"area":"mllm"},{"id":"2506.18164","title":"CDG-MAE: Cross-view Masked Modeling using Diffusion Generated Views","created":"2025-06-22","cited_by_count":0,"area":"diffusion"},{"id":"2509.02029","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.15194","title":"Salient Concept-Aware Generative Data Augmentation","created":"2025-10-16","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":"2511.01517","title":"NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2603.02554","title":"Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation","created":"2026-03-03","cited_by_count":0,"area":"distill"},{"id":"2607.02637","title":"Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":null}