Yuxin Chen

8 papers University of Pennsylvania

• Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
• Deployment Efficient Reward-Free Exploration with Linear Function Approximation
• EditInfinity: Image Editing with Binary-Quantized Generative Models
• Formal Models of Active Learning from Contrastive Examples
• MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
• Riemannian Consistency Model
• The Emergence of Abstract Thought in Large Language Models Beyond Any Language
• Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization