Liping Li

About

Liping Li, MS, PhD, BMD, is an Assistant Professor of Practice in the Department of Pathology, Immunology and Laboratory Medicine at Rutgers New Jersey Medical School. She earned her Master of Science degree in 2018 from NJIT, her PhD in 2009 from Temple University, and her Bachelor of Medical Degree in 1997 from Zhengzhou University (Henan Medical University). She holds medical licensure in New Jersey. The provided information does not include specific details about her research focus or key contributions.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Mathematics
• Algorithm
• Pharmacology
• Real-time computing
• Embedded system
• Medicine
• Computer vision

Selected publications

• Understanding Domain Randomization for Sim-to-real Transfer

  arXiv (Cornell University) · 2021 · 33 citations

  Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most popular algorithms for sim-to-real transfer -- has been demonstrated to be effective in various tasks in robotics and autonomous driving. Despite its empirical successes, theoretical understanding on why this simple algorithm works is limited. In this paper, we pr…

  DOI

• WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

  2025-01-01 · 1 citations

  articleOpen accessSenior author

  Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

  PublisherOA PDFDOI

• SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs

  ArXiv.org · 2025-09-25

  preprintOpen accessSenior author

  Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their general capabilities. In this work, we revisit this trade-off and present both empirical and theoretical insights. First, we show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation while preserving comparable target-domain performance. We then provide a t…

  PublisherOA PDFDOI

• WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

  ArXiv.org · 2025-05-22

  preprintOpen accessSenior author

  While reinforcement learning (RL) has demonstrated remarkable success in enhancing large language models (LLMs), it has primarily focused on single-turn tasks such as solving math problems. Training effective web agents for multi-turn interactions remains challenging due to the complexity of long-horizon decision-making across dynamic web interfaces. In this work, we present WebAgent-R1, a simple yet effective end-to-end multi-turn RL framework for training web agents. It learns directly from on…

  PublisherOA PDFDOI

Frequent coauthors

• Yu Wu

  Sichuan Agricultural University

  145 shared

• Gen Li

  105 shared

• Rui Zhu

  Beijing Institute of Technology

  49 shared

• Bin Jiang

  Nanjing University of Aeronautics and Astronautics

  44 shared

• John Langford

  33 shared

• Bin Jiang

  Nanjing University of Aeronautics and Astronautics

  33 shared

• Mingyan Li

  Soochow University

  25 shared

• D. Eremina

  Stony Brook University

  22 shared

Education

• Other

  Zhengzhou University (Henan Medical University)

  1997

• Ph.D.

  Temple University

  2009

• M.S.

  NJIT

  2018

Similar researchers at Rutgers University

• Saul Susterh-89
• Dane Parkerh-39
• Sukhwinder Singhh-34