Scholar
Yu Yang
Google Scholar ID: KK6Yj4IAAAAJ
OpenAI
Citations & Impact
Citations
1,148
H-index
18
i10-index
23
Publications
20
Co-authors
20
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published multiple papers including 'AIR-BENCH 2024: A Safety Benchmark Based on Regulation and Policies Specified Risk Categories' (ICLR 2025), 'SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models' (NeurIPS 2024), 'Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias' (AISTATS 2024), etc. Received the UCLA Dissertation Award and Outstanding Graduate Student Research Award.
Research Experience
- Currently working on the reasoning team at OpenAI.
Education
- Received a Ph.D. in Computer Science from the University of California, Los Angeles (UCLA) in 2024. Studied mathematics, statistics, and some brain and mind in college (also at UCLA).
Background
- Research interests include how training data quality, distribution, and curriculum influence model performance and training efficiency. Collaborated with researchers from Google DeepMind, Microsoft Research, Meta FAIR, and NVIDIA Research.
Miscellany
- Used to live in Beijing and Los Angeles, now based in San Francisco.
