William Overman
Scholar

William Overman

Google Scholar ID: B2XPxEkAAAAJ
PhD Student, Stanford GSB
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
260
 
H-index
3
 
i10-index
2
 
Publications
11
 
Co-authors
0
 
Contact
CVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
9 items
Planning Against Learning in Rank-1 Games
2026
Cited
0
Annealed Softmax Greedy in Many-Armed Bayesian Bandits
2026
Cited
0
Calibrating Conservatism for Scalable Oversight
2026
Cited
0
Causal Effects with Unobserved Unit Types in Interacting Human-AI Systems
2026
Cited
0
The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
2025
Cited
0
On Aligning Prediction Models with Clinical Experiential Learning: A Prostate Cancer Case Study
2025
Cited
0
Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
2025
Cited
0
Can We Validate Counterfactual Estimations in the Presence of General Network Interference?
2025
Cited
0
Resume
Academic Achievements
  • NeurIPS 2025: Published 'The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy' and 'Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models'.
  • NeurIPS 2024: Published 'Aligning Model Properties via Conformal Risk Control' and 'Higher-Order Causal Message Passing for Experimentation with Complex Interference'.
  • ICLR 2022: Sole student author of 'Global convergence of multi-agent policy gradient in markov potential games'.
  • AISTATS 2022: Sole student author of 'Independent natural policy gradient always converges in markov potential games'.
  • arXiv 2025: Multiple preprints accepted, including works on counterfactual estimation under network interference and alignment with clinical experiential learning.
  • Paper 'Can We Validate Counterfactual Estimations in the Presence of General Network Interference?' accepted for oral presentation at CODE@MIT 2025 and presentation at MSOM TIE SIG 2025.