Min Cai

TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller

DataSciBench: An LLM Agent Benchmark for Data Science