Shuchang Tao

reinforcement learning (3) large language model (2) chain-of-thought reasoning (1) preference optimization (1) code generation (1) confidence calibration (1) reward function (1) multi-step planning (1) software engineering (1) weak-to-strong learning (1) supervised fine-tuning (1) student model (1) tool learning (1) error diagnosis (1) function scaffold (1) diffusion language model (1) tool calling (1) response quality (1) context learning (1) function implementation (1)