影响力指数

46.01/100

前 10.4%

全站排名 #6,679

发表论文4 篇

平均评分5.7

年均产出2.0 篇/年

William Overman

PhD student@Stanford University·美国·OpenReview

研究方向

AI safety · AI alignment · Causal Inference · Reinforcement Learning

Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models

NeurIPS 2025Poster

Beating Price of Anarchy and Gradient Descent without Regret in Potential Games

ICLR 2024Poster

Aligning Model Properties via Conformal Risk Control

NeurIPS 2024Poster

Higher-Order Causal Message Passing for Experimentation with Complex Interference

NeurIPS 2024Poster

合作者 (10)

博士导师3 篇

Georgios Piliouras

Ioannis Panageas

Stefanos Leonardos

Stelios Andrew Stavroulakis