Jonathan Daniel Chang

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

Value-Guided Search for Efficient Chain-of-Thought Reasoning

Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF

Critique-out-Loud Reward Models