影响力指数

20.08/100

前 41.3%

全站排名 #26,605

发表论文2 篇

平均评分6.6

年均产出2.0 篇/年

Rishub Tamirisa

Undergrad student@University of Illinois, Urbana-Champaign·美国·OpenReview

研究方向

ai safety · adversarial robustness · code generation · LM agents

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

NeurIPS 2025Spotlight

Tamper-Resistant Safeguards for Open-Weight LLMs

ICLR 2025Poster

合作者 (20)

Bhrugu Bharathi