Runze Liu

reward learning (2) preference-based reinforcement learning (2) reinforcement learning (1) mathematical reasoning (1) preference learning (1) chain-of-thought reasoning (1) policy learning (1) human feedback (1) adversarial attack (1) vision-language model (1) bi-level optimization (1) data efficiency (1) human preference (1) process reward model (1) test-time scaling (1) reinforcement learning framework (1) targeted behavior attack (1) policy manipulation (1) intention policy (1) code verification (1)