Scholar
Yifei He
Google Scholar ID: VgfCr8MAAAAJ
CS PhD student, University of Illinois Urbana-Champaign
Citations & Impact
Citations
162
H-index
8
i10-index
8
Publications
14
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 'MergeBench' accepted at NeurIPS 2025; work on efficient MoE editing accepted at EMNLP 2025; 'Multilingual Scaling Laws' accepted at ACL 2025; work on mechanistic interpretability accepted at NAACL 2025; 'Localize-and-Stitch' accepted by TMLR; 'Semi-Supervised Reward Modeling (SSRM)' accepted at EMNLP 2024; work on robust multi-task learning accepted at ICML 2024; work on gradual domain adaptation accepted at JMLR.
Research Experience
- Interned at Microsoft Turing, Microsoft GenAI, and Amazon Search Science & AI. Currently on the job market for full-time industry research scientist positions, starting summer 2026.
Education
- Ph.D. student in Computer Science at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Han Zhao; dual bachelor’s degree in Data Science from the University of Michigan (UM) and in Electrical and Computer Engineering from Shanghai Jiao Tong University (SJTU).
Background
- Research interests: Making foundation models and agents learn from multiple sources and tasks in an efficient, robust, and scalable manner. Specific areas of work include multimodal agents for computer use, multi-domain learning for foundation models (model merging, multilingual LLMs), LLM data (reward modeling), and inference efficiency (MoE). Previously worked on multi-objective optimization, domain adaptation, and multimodal learning.
Miscellany
- Personal interests and hobbies not mentioned.
