PPL
Xinyu Fang
Papers (4)
Beyond Mode Collapse: Distribution Matching for Diverse ReasoningForge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMsOPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search SpacesOn the Role of Language Representations in Auto-Bidding: Findings and Implications