Akbir Khan

~Akbir_Khan1

4

论文总数

4.0

年均投稿

6.0

平均评分

接收情况3/4

会议分布

ICLR

4

发表论文 (4 篇)

20254 篇

Language Models Learn to Mislead Humans via RLHF

ICLR 2025Poster

Shell Games: Control Protocols for Adversarial AI Agents

ICLR 2025withdrawn

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

ICLR 2025Poster

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

ICLR 2025Poster

合作者 (20)

Aryan Bhatt2 篇

Buck Shlegeris2 篇

Ethan Perez2 篇

Jiaxin Wen2 篇

Bartłomiej Cupiał1 篇

Davide Paglieri1 篇