影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
38.56/100
前 15.5%
全站排名 #9,960
发表论文5 篇
平均评分
年均产出2.5 篇/年
Akbir Khan
研究方向
Multi-agent Reinforcement Learning · AI Safety · Large Language Models
16
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
ICLR 2025Poster
通讯20
Language Models Learn to Mislead Humans via RLHF
ICLR 2025Poster
三作30
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
ICLR 2025Poster
5
Shell Games: Control Protocols for Adversarial AI Agents
ICLR 2025Withdrawn