Chen Zhu

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Multi-Sample Preference Optimization for Generative Model Alignment

Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization

Boosting LLM Reasoning via Spontaneous Self-Correction

Preference Optimization with Multi-Sample Comparisons

The Perfect Blend: Redefining RLHF with Mixture of Judges

OPTune: Efficient Online Preference Tuning