Rui Feng

The paper proposes R-CoT, a reasoning-layer watermarking framework that embeds ownership watermarks directly into the stable reasoning path of LLMs, achieving high robustness against perturbations.

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step reasoning.

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in RL performance.