William Overman
PhD, Stanford GSB
My research develops approaches to AI safety, focused on how humans can effectively oversee AI systems whose capabilities increasingly surpass their own.
I'm a Ph.D. student in Operations, Information, and Technology at Stanford Graduate School of Business, advised by Mohsen Bayati. Before Stanford, I was a visiting researcher at the Institute for Basic Science in South Korea and earned an M.Sc. in Computer Science from UC Irvine. I graduated from Caltech with a double major in Mathematics and Computer Science.
Selected Work
2026
Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems
Workshop on Technical AI Governance Research @ ICML 2026
2025
Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
NeurIPS 2025
2024
Aligning Model Properties via Conformal Risk Control
NeurIPS 2024
2022
All papers →
News
- 2026.09 Invited talk at Seoul National University: "Control of Increasingly Capable AI Systems with Safety Guarantees"
- 2026.09 Will mentor the SPAR project titled "Benchmarking When to Apply Oversight for Agentic AI"
- 2026.07 Presented two posters at ICML 2026: "Calibrating Conservatism for Scalable Oversight" and "The Oversight Game"
- 2026.05 Successfully defended Ph.D. dissertation at Stanford