Zhuohao Yu

From Curiosity to Caution: Mitigating Reward Hacking for Best-of-$N$ with Pessimism

TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them

RewardAnything: Generalizable Principle-Following Reward Models

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders

An Empirical Analysis of Uncertainty in Large Language Model Evaluations

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation