AI Alignment
William Overman
PhD at Stanford
RL
About
I’m a PhD student at Stanford advised by Mohsen Bayati. I’m passionate about AI safety and alignment, especially obtaining results with provable guarantees. My research also spans reinforcement learning, causal inference, and black-box uncertainty quantification, with particular interest in how each might intersect with AI alignment.
Education
2022 — Now
Ph.D. at Stanford
Graduate School of Business, Operations, Information, and Technology
2020 — 2022
M.S. at UC Irvine
Computer Science
2016 — 2020
B.S. at Caltech
Mathematics and Computer Science
Selected Papers
2025
Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
W. Overman, M. Bayati
Preprint
AI Alignment
2024
Aligning Model Properties via Conformal Risk Control
W. Overman, J.J. Vallon, M. Bayati
NeurIPS 2024
AI Alignment
2022
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
S. Leonardos, W. Overman,
I. Panageas, G.Piliouras
ICLR 2022
RL
2025
Can We Validate Counterfactual Estimations in the Presence of General Network Interference?
S. Shirani, Y. Luo, W. Overman, R. Xiong, M. Bayati
Preprint
Causal Inference
2024
Higher-Order Causal Message Passing for Experimentation with Complex Interference
M. Bayati, Y. Luo, W. Overman, S. Shirani, R. Xiong
NeurIPS 2024
Causal Inference
Industry Experience
2023 —
PhD Scientist Intern
Uber
2025
AI Consultant
Jingo (pre-seed startup)
Links
AI Alignment
William Overman
PhD at Stanford
Reinforcement Learning
About
I’m a PhD student at Stanford advised by Mohsen Bayati. I’m passionate about AI safety and alignment, especially obtaining results with provable guarantees. My research also spans reinforcement learning, causal inference, and black-box uncertainty quantification, with particular interest in how each might intersect with AI alignment.
Education
2022 — Now
Ph.D. at Stanford
Graduate School of Business, Operations, Information, and Technology
2020 — 2022
M.S. at UC Irvine
Computer Science
2016 — 2020
B.S. at Caltech
Mathematics and Computer Science
Selected Papers
2025
Conformal Arbitrage: Risk-Controlled Balancing of Competing
Objectives in Language Models
W. Overman, M. Bayati
Preprint
AI Alignment
2024
Aligning Model Properties via Conformal Risk Control
W. Overman, J.J. Vallon, M. Bayati
NeurIPS 2024
AI Alignment
2022
Global Convergence of Multi-Agent Policy Gradient in
Markov Potential Games
S. Leonardos, W. Overman, I. Panageas, G. Piliouras
ICLR 2022
Reinforcement Learning
2025
Can We Validate Counterfactual Estimations in the Presence of
General Network Interference?
S. Shirani, Y. Luo, W. Overman, R. Xiong, M. Bayati
Preprint
Causal Inference
2024
Higher-Order Causal Message Passing for Experimentation with
Complex Interference
M. Bayati, Y. Luo, W. Overman, S. Shirani, R. Xiong
NeurIPS 2024
Causal Inference
Industry Experience
2023 —
PhD Scientist Intern
Uber
2025
AI Consultant
Jingo (pre-seed startup)
Links