Marcus Williams

~Marcus_Williams1

2

论文总数

1.0

年均投稿

6.5

平均评分

接收情况2/2

会议分布

ICLR

2

发表论文 (2 篇)

20251 篇

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

ICLR 2025Poster

20241 篇

On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning

ICLR 2024Poster

合作者 (10)

Charlie Griffin1 篇

Halfdan Holm1 篇

Joar Max Viktor Skalse1 篇

Max Heitmann1 篇

Rohan Subramani1 篇

Adhyyan Narang1 篇

Anca Dragan1 篇

Brendan Murphy1 篇