2 papers
cs.LG2024
DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure
Yunfan Xiong, Ruoyu Zhang, Yanzeng Li +2
While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly b…
cs.CL2024
Leveraging Large Language Model as Simulated Patients for Clinical Education
Yanzeng Li, Cheng Zeng, Jialun Zhong +3
Simulated Patients (SPs) play a crucial role in clinical medical education by providing realistic scenarios for student practice. However, the high cost of training and hiring qual…