Gene Yang

I am a Computer Science student at Carnegie Mellon University interested in why machines learn (via pretraining science and interpretability), and how to make them learn (via reinforcement learning).

I am fortunate to be in the CMU AI & Reinforcement Learning ("AIRe") lab under the supervision of Prof. Aviral Kumar. Previously, I worked on scaling laws and synthetic data for market foundation models at HRT, RL for tool calling LLMs at Scale AI, and evals at the Center for AI Safety.

Email  /  Linkedin  /  Github

profile photo
Education
CMU Carnegie Mellon University
B.S. in Computer Science, 2027
GPA: 3.96/4.0
Relevant Coursework: Machine Learning, Deep Learning, Deep Reinforcement Learning, Deep Learning Systems, Algorithm Design and Analysis, Parallel and Sequential Data Structures and Algorithms, Computer Systems, Vector Analysis, Matrix Theory, Probability and Computing, Neural Computation, etc.
Teaching
10703 - Deep Reinforcement Learning (Teaching Assistant)
Spring 2025, Fall 2025, Fall 2026
Other Interests
Honor of Kings, Robotics, TCS, and eating

Website template from Jon Barron.
Last updated: 2025.