基本信息
浏览量:0
职业迁徙
个人简介
Research Highlights
I work on algorithms and theory for interactive agents that continuously operate in the complex environments. To this end, I use and develop fundamental tools in probability, optimization, game theory and information theory.
I designed “HyperAgent”, which quantifies epistemic uncertainty on optimal value function
, provides scalable solutions for real-time sequential decision making.
HyperAgent can be used for human-AI alignment and collaboration, e.g. GPT-HyperAgent for online content moderation from human feedback.
HyperAgent can be used for controlling LLM decoding towards high outcome feedback.
I am working on reliable and safe solutions for customer, healthcare and business operations, via inference-time algorithms that leverages powerful cloud computing services on foundation models while augmenting necessary algorithmic modules in end devices.
I work on algorithms and theory for interactive agents that continuously operate in the complex environments. To this end, I use and develop fundamental tools in probability, optimization, game theory and information theory.
I designed “HyperAgent”, which quantifies epistemic uncertainty on optimal value function
, provides scalable solutions for real-time sequential decision making.
HyperAgent can be used for human-AI alignment and collaboration, e.g. GPT-HyperAgent for online content moderation from human feedback.
HyperAgent can be used for controlling LLM decoding towards high outcome feedback.
I am working on reliable and safe solutions for customer, healthcare and business operations, via inference-time algorithms that leverages powerful cloud computing services on foundation models while augmenting necessary algorithmic modules in end devices.
研究兴趣
论文共 10 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
International Conference on Artificial Intelligence and Statistics (2024): 559-567
引用0浏览0EI引用
0
0
International Conference on Learning Representations (ICLR) (2022)
引用5浏览0EI引用
5
0
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn