Yoshua Y. Li

collaborators

3 papers

cs.CL2026

RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generation

Xinlong Xu, Yoshua Y. Li

Retrieval-augmented generation treats an external corpus as inference evidence, allowing injected documents to promote attacker-chosen claims. Existing detectors depend on trusted…

math.RT2026

Minimal Nilpotent Orbits of type G2, F4 and E8

Boming Jia

Let $g$ be a complex simple Lie algebra of type $G_{2}$ , $F_{4}$ , or $E_{8}$ . We prove that the closure $O_{m i n} (g)$ of its minimal nilpotent orb…

cs.LG2026

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

Yifan Ding, Xincheng Wei, Yoshua Y. Li +7

Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stron…