Value-Based Pre-Training with Downstream Feedback
Shuqi Ke, Giulia Fanti
preprint · 2026
I am a Ph.D. student at Carnegie Mellon University, advised by Prof. Giulia Fanti. I work to close the generalization and sample efficiency gap between AI and human.
Value-Based Pre-Training with Downstream Feedback
Shuqi Ke, Giulia Fanti
preprint · 2026
Characterizing the Training Dynamics of Private Fine-Tuning with Langevin Diffusion
Shuqi Ke, Charlie Hou, Sewoong Oh, Giulia Fanti
TMLR · 2025
Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
Zhihan Liu, Hao Hu, Shenao Zhang, Hongyi Guo, Shuqi Ke, Boyi Liu, Zhaoran Wang
ICML · 2024