Zheyuan Yang

reinforcement learning (1) benchmark evaluation (1) fact verification (1) knowledge distillation (1) code generation (1) llm evaluation (1) fault detection (1) multilingual benchmark (1) test case generation (1) table reasoning (1) group relative policy optimization (1) inference-time scaling (1) large language model (1) verifiable reward (1) fault coverage (1) reinforcement learning with verifiable reward (1) inference time scaling (1) distillation from reasoning trace (1) foundation model evaluation (1) algorithm problem (1)