☕️About Me
Xuhong Wang is an assistant researcher at the Shanghai AI Laboratory. He graduated from Sichuan University with a Bachelor’s degree in 2017, and obtained his Ph.D. from the Shanghai Jiao Tong University in 2022. His main research focus during his doctoral studies was graph learning and knowledge mining. Recently, his research focuses on training self-evolving trustworthy agents. Detailed pub list Google Scholar homepage. The research center has long-term openings for intern positions, co-trained doctoral students, algorithm engineers, and researchers. Welcome to inquire via email (wangxuhong@pjlab.org.cn).
- Mutli-model Large Language Model
- Self-evolving Memory System
- Reinforcement Learning with Environment Feedback
PhD Artificial Intelligence
Shanghai Jiao Tong University
BSc Electronices Engineering
Sichuan University
[2025.11] As the sole corresponding author, a LLM reward model based on uncertainty modeling was presented at the EMNLP 2025 Main (Oral), which can significantly improve the content thinking quality of large model inference training.
[2025.8] As the sole corresponding author, a distributed KV Cache architecture optimized for MoE models was released (PiKV: KV Cache Management System for Mixture of Experts)(https://arxiv.org/abs/2508.06526).
[2025.8] Released the SOTA CoT-PRM model (VRPRM), achieving Test-time Scaling effect of Best-of-N approaching the theoretical limit value Pass@K, surpassing the SOTA model by 118% with only 1/8 of traning data.
[2025.8] A unified model NaviMaster has been released that can operate both the digital GUI interface and real-world navigation simultaneously.
[2025.6] As the corresponding author, he guided the internship student to submit a paper, which was included in ICCV 2025. The relevant achievements have refreshed the SOTA of multi-modal retrieval, and it can provide the function of precise memory retrieval for embodied AI with 500,000 frames. demo
[2024.10] Join Safety and Trustworthy AI Center in the Shanghai AI Laboratory, responsible for knowledge enhancement for LLMs.
[2023.10] First author paper, using a dynamic graph network evolution engine for accelerated simulation of complex transportation systems.
[2022.10] Join Shanghai AI Laboratory, mainly responsible for AI security evaluation systems and multi-agent simulation platforms. I earned an ‘Excellent’ performance rating for two consecutive years.
[2022.3] Collaborative paper published in Nature Machine Intelligence.
[2020.2] Life’s first paper was published in Knowledge-Based Systems