Simon Du

6 papers University of Washington

• A Minimalist Example of Edge-of-Stability and Progressive Sharpening
• Deployment Efficient Reward-Free Exploration with Linear Function Approximation
• Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
• Reinforcement Learning for Reasoning in Large Language Models with One Training Example
• Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
• Understanding the Gain from Data Filtering in Multimodal Contrastive Learning