Kevin Zhang
Machine Learning Researcher
About
Research scientist focused on large language model alignment,
reinforcement learning from human feedback, and scalable
inference systems. Previously at Google DeepMind.
Publications
- Efficient Sparse Attention for Long-Context Transformers (NeurIPS 2025)
- Reward Model Scaling Laws in RLHF (ICML 2024)
- On the Geometry of Latent Representations in Diffusion Models (ICLR 2024)
Education
Stanford University — Ph.D. Computer Science, 2022
UC Berkeley — B.S. EECS, 2017
Contact
Email: kevin@siminliu.com