Scholar
Jing-Cheng Pang
Google Scholar ID: R3Y_WrkAAAAJ
Researcher, Huawei; Nanjing University
Citations & Impact
Citations
245
H-index
8
i10-index
8
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including 'ReViWo' at ICLR 2025, 'KALM' at NeurIPS 2024, and 'InCLET' at AAMAS 2025. He was also recognized as a Top Reviewer (top 8%) for NeurIPS 2023.
Research Experience
- During his PhD, he focused on integrating reinforcement learning (RL) and large language models (LLMs) to develop systems that can interpret human intent and act autonomously in dynamic environments. Specific areas of study included: language-conditioned RL, optimization algorithms, imitation learning, generalist agent, LLM training, and embodied AI. Currently, he is exploring how to use RL and LLMs to build Domain Agents capable of performing complex tasks in specific domains.
Education
- Received BSc from the University of Electronic Science and Technology of China (UESTC) in June 2019; Obtained PhD from Nanjing University (LAMDA Group) in June 2025, supervised by Prof. Yang Yu; Visiting scholar with Prof. Masashi Sugiyama’s team at RIKEN-AIP, Tokyo, Japan from July to October 2024.
Background
- Currently an AI Researcher at Huawei, focusing on building Domain Agent through reinforcement learning and large language models. His research interests include connecting humans and intelligent agents via natural language.
