Author

Yinghui He

Observed name: He, Yinghui

Institutions: Nvidia (United Kingdom), Princeton University, Nvidia (United States)

Observed institutions: Nvidia (United Kingdom), Princeton University, Nvidia (United States)

OpenAlex ID: A5136483865

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

2026 · He, Yinghui, Kaur, Simran, et al. · arXiv (Cornell University) · 76

MixSD: Mixed Contextual Self-Distillation for Knowledge Injection

2026 · Liu, Jiarui, Zhang, Lechen, et al. · arXiv (Cornell University) · 4

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

2026 · Liu, Jiarui, Tao, Renjie, et al. · arXiv (Cornell University) · 3

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

2026 · He, Yinghui, Yang, Ling, et al. · arXiv (Cornell University) · 1

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

2026 · He, Yinghui, Chang, Yapei, et al. · arXiv (Cornell University)

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

2026 · Wu, Yufan, He, Yinghui, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 84

H-index: 3

I10-index: 1