Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

出版物
In USENIX Symposium on Operating Systems Design and Implementation (OSDI)
Shuzhang Zhong
PhD Student (2023)
Haochen Huang
PhD Student (2026)
Shengxuan Qiu
PhD Student (2027)
李萌
李萌
助理教授

我通过算法—硬件协同设计,研究高效且保护隐私的人工智能系统,并将其应用于大语言模型、具身智能和多模态智能。