Junyuan Hong
Junyuan Hong
Research
Publications
Experiences
Teaching
Efficiency
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
A training-free approach that calibrates chain-of-thought reasoning in LLMs, improving accuracy while reducing computational overhead.
Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization
Efficient and federated learning for heterogeneous clients with different memory sizes
Cite
×