Short bio
I am a Lecturer (Assistant Professor) in the Department of Computer Science at The University of Manchester. Prior to joining Manchester, I was a Researcher at Microsoft Research Cambridge from 2020 to 2022, and concurrently a Research Associate at the University of Oxford during the same period. I received my Ph.D. from the Hong Kong University of Science and Technology (HKUST) in 2020, and my bachelor’s degree from the University of Science and Technology of China (USTC) in 2015.
My research centers on artificial intelligence, particularly deep reinforcement learning and generative models. I work on large-scale reinforcement learning, policy gradient methods, generative modeling, and optimization, with applications in video games, robotics, and multi-agent systems.
Recent updates:
- 2026-04-30: One paper accepted to ICML 2026
- 2026-01-22: One paper accepted to AISTATS 2026
- 2026-01-13: One paper accepted to TMLR
- 2025-10-06: Awarded Open Source AI Fellowship by Alan Turing Institute
- 2025-09-25: One paper accepted to NeurIPS AI4Science workshop
- 2025-08-26: One paper accepted to ICDM
- 2025-07-18: Received UKRI AI Research Resource (AIRR) Early Access Project award
- 2025-07-10: Awarded Fellow of Advance HE (FHEA)
- 2025-06-16: One paper accepted to TMLR
- 2025-02-24: Funding award (PI): EPSRC Doctoral Landscape Award (DLA) Studentship
- 2025-01-28: One paper accepted to ICRA 2025
- 2024-10-01: Funding award (PI): TICM Collaborative R&D programme: Reinforcement Learning for Fully Automated System Calibration
- 2024-07-17: Funding award (Co-I) of Generative Modeling for Engineering Design, sponsored by Cummins Turbo Technologies Ltd, collaboratively with Dr Wei Pan and Dr Alex Skillen
- 2024-06-18: Received School of Engineering Pump Priming, Theme Development and Dissemination fund
- 2024-05-17: One paper accepted to KDD 2024
- 2024-02-01: Funding award (Co-I) of AI Hub in Generative Models, collaboratively with Professor David Barber
- 2023-12-14: One paper accepted to IUI 2024
- 2023-10-31: Funding award (Co-I) of UKRI AI Centre for Doctoral Training in Decision Making for Complex Systems, collaboratively with Dr Mauricio Alvarez
- 2023-10-03: Quality Champion Award for the ECAI Reviewer
- 2023-09-22: One paper accepted to NeurIPS 2023
- 2023-06-21: One proposal accepted to AAAI 2023 Fall Symposium Series
- 2023-06-01: Best Paper Award at AAMAS 2023
- 2023-05-16: One paper accepted to CoLLAs 2023
- 2023-01-20: One paper accepted to ICLR 2023
- 2023-01-03: One paper accepted to AAMAS 2023
- 2022-12-07: Joined University of Manchester as a lecturer
Publications
You can also find my articles on my Google Scholar profile.
Year 2026
- Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation, Mingfei Sun, ICML 2026
- Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning, Yingxiao Huo, Satya Prakash Dash, Radu Stoican, Samuel Kaski, Mingfei Sun, TMLR
- Gradient Regularized Natural Gradients, Satya Prakash Dash, Hossein Abdi, Wei Pan, Samuel Kaski, Mingfei Sun, AISTATS 2026
Year 2025
- Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks, Matteo Tucat, Anirbit Mukherjee, Mingfei Sun, Procheta Sen, Omar Rivasplata, TMLR
- Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering, Hossein Abdi, Mingfei Sun, Wei Pan, ICDM 2025
- DroneDiffusion: Robust quadrotor dynamics learning with diffusion models, Avirup Das, Rishabh Dev Yadav, Sihao Sun, Mingfei Sun, Samuel Kaski, Wei Pan, ICRA 2025
Year 2024
- Effective generation of feasible solutions for integer programming via guided diffusion, Hao Zeng, Jiaqi Wang, Avirup Das, Junying He, Kunpeng Han, Haoyuan Hu, Mingfei Sun, KDD 2024
- FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers’ Preference Elicitation, Hanfang Lyu, Yuanchen Bai, Xin Liang, Ujaan Das, Chuhan Shi, Leiliang Gong, Yingchi Li, Mingfei Sun, Ming Ge, Xiaojuan Ma, IUI 2024
Year 2023
- Smacv2: An improved benchmark for cooperative multi-agent reinforcement learning, Benjamin Ellis, Jonathan Cook, Skander Moalla, Mikayel Samvelyan, Mingfei Sun, Anuj Mahajan, Jakob Foerster, Shimon Whiteson, NeurIPS 2023
- Comparing the efficacy of fine-tuning and meta-learning for few-shot policy imitation, Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann, Richard E Turner, Conference on Lifelong Learning Agents 2023
- Modeling adaptive expression of robot learning engagement and exploring its effects on human teachers, Shuai Ma, Mingfei Sun, Xiaojuan Ma, ACM Transactions on Computer-Human Interaction
- Imitating human behaviour with diffusion models, Tim Pearce, Tabish Rashid, Anssi Kanervisto, Dave Bignell, Mingfei Sun, Raluca Georgescu, Sergio Valcarcel Macua, Shan Zheng Tan, Ida Momennejad, Katja Hofmann, Sam Devlin, ICLR 2023
- Trust Region Bounds for Decentralized PPO Under Non-stationarity, Mingfei Sun, Sam Devlin, Jacob Beck, Katja Hofmann, Shimon Whiteson, AAMAS 2023 Best Paper Award
Year 2022
- How humans perceive human-like behavior in video game navigation, Evelyn Zuniga, Stephanie Milani, Guy Leroy, Jaroslaw Rzepecki, Raluca Georgescu, Ida Momennejad, Dave Bignell, Mingfei Sun, Alison Shaw, Gavin Costello, Mikhail Jacob, Sam Devlin, Katja Hofmann, CHI Extended Abstract
- UniMASK: Unified Inference in Sequential Decision Problems, Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin, NeurIPS 2022
- Investigating the Effects of Robot Engagement Communication on Learning from Demonstration, Mingfei Sun, Zhenhui Peng, Meng Xia, Xiaojuan Ma, International Journal of Social Robotics
Year 2021
- Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency, Mingfei Sun, Sam Devlin, Katja Hofmann, Shimon Whiteson, AAAI 2022
- CrowdPatrol: A mobile crowdsensing framework for traffic violation hotspot patrolling, Zhihan Jiang, Hang Zhu, Binbin Zhou, Chenhui Lu, Mingfei Sun, Xiaojuan Ma, Xiaoliang Fan, Cheng Wang, Longbiao Chen, IEEE Transactions on Mobile Computing
Year 2020
- Supervised learning achieves human-level performance in moba games: A case study of honor of kings, Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, IEEE Transactions on Neural Networks and Learning Systems
- Mastering complex control in moba games with deep reinforcement learning, Deheng Ye, Zhao Liu, Mingfei Sun, Bei Shi, Peilin Zhao, Hao Wu, Hongsheng Yu, Shaojie Yang, Xipeng Wu, Qingwei Guo, Qiaobo Chen, Yinyuting Yin, Hao Zhang, Tengfei Shi, Liang Wang, Qiang Fu, Wei Yang, Lanxiao Huang, AAAI 2020
Year 2019
- Adversarial imitation learning from incomplete demonstrations, Mingfei Sun, Xiaojuan Ma, IJCAI 2019
- Peerlens: Peer-inspired interactive learning path planning in online question pool, Meng Xia, Mingfei Sun, Huan Wei, Qing Chen, Yong Wang, Lei Shi, Huamin Qu, Xiaojuan Ma, CHI 2019
- Estimating emotional intensity from body poses for human-robot interaction, Mingfei Sun, Yiqing Mou, Hongwen Xie, Meng Xia, Michelle Wong, Xiaojuan Ma, IEEE SMC 2019
Year 2018
- A neural-network-based investigation of eye-related movements for accurate drowsiness estimation, Mingfei Sun, Masanori Tsujikawa, Yoshifumi Onishi, Xiaojuan Ma, Atsushi Nishino, Satoshi Hashimoto, IEEE EMBC 2018
Year 2017
- Sensing and handling engagement dynamics in human-robot interaction involving peripheral computing devices, Mingfei Sun, Zhenjie Zhao, Xiaojuan Ma, CHI 2017