Curriculum Vitae

A printable PDF version is available here.

Education

  • PhD candidate, Graduate School of Information Science and Technology, The University of Tokyo (Tsukada Lab). Sep 2023 – Sep 2026 (expected). Thesis: Safe and Efficient Generative Models for Autonomous Driving: From Preference-Aligned VLA to Real-Time Diffusion Planning.
  • M.Eng. in Information and Communications Engineering, Tokyo Institute of Technology. Sep 2021 – Sep 2023. GPA 3.57 / 4.0.
  • B.Eng. in Vehicle Engineering, Jilin University (China). Sep 2017 – Jun 2021. GPA 3.4 / 4.0. Exchange at Nagoya University (Japan).

Honors and fellowships

  • JSPS Research Fellowship for Young Scientists (DC2), 2026 – 2028. Grant No. 26KJ0799 — Driving Decision Making by LLM Reinforcement Learning Combining Fast and Slow Thinking. KAKEN page.
  • SPRING GX Fellowship, The University of Tokyo, 2024 – 2026.
  • WISE-SSS Core Research Grant, Tokyo Institute of Technology, 2022 – 2023.

Research experience

  • Huawei 2012 Laboratories, Shenzhen. Research Intern. Jul – Nov 2025. Designed a world-model-based trajectory generation framework for autonomous driving. Built protocols to quantify safety-constraint violations and control smoothness, with seed-fixed splits for reproducibility. Reduced inference latency by integrating DPM-Solver (ODE-based diffusion sampling).
  • TIER IV, Inc., Tokyo. Student Researcher. Apr 2024 – present. Verification of Autoware and LLM-based decision-making modules. Built a minimum-viable experimental environment with engineers to iterate quickly on metrics and visualizations.
  • Carnegie Mellon University, Nakahira Lab, Pittsburgh, PA. Visiting Scholar. Apr – May 2025. Latent Safety Detection framework. VLM-based extraction of long-tail failure cases via grounding driving instructions to latent representations.
  • NEC Data Science Research Laboratories, Kanagawa. Research Intern. Aug – Sep 2022. Optimal path planning for factory robots via Deep RL; encoded safety constraints in the reward; full R&D cycle in two months.
  • State Key Lab of Auto Simulation & Control, Jilin University, Changchun. Research Assistant. Sep 2020 – Sep 2022. Three IEEE Transactions papers on constrained safe RL for autonomous driving.

Publications

Refereed international conference proceedings (first author)

  1. Yun Li, E. Javanmardi, S. Thompson, K. Katsumata, A. Orsholits, M. Tsukada. “Multi-PrefDrive: Optimizing Large Language Models for Autonomous Driving Through Multi-Preference Tuning.” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025. (Top robotics conference)
  2. Yun Li, E. Javanmardi, S. Thompson, K. Katsumata, A. Orsholits, M. Tsukada. “PrefDrive: Enhancing Autonomous Driving through Preference-Guided Large Language Models.” IEEE Intelligent Vehicles Symposium (IV), Cluj-Napoca, Romania, 2025.
  3. Yun Li, K. Katsumata, E. Javanmardi, M. Tsukada. “Large Language Models for Human-like Autonomous Driving Decision Making: A Survey.” IEEE International Conference on Intelligent Transportation Systems (ITSC), Edmonton, Canada, 2024.
  4. Yun Li, S. Thompson, Y. Zhang, E. Javanmardi, M. Tsukada. “An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous Driving.” IEEE ITSC, Naples, Italy, 2026.
  5. Yun Li, E. Javanmardi, Y. Zhang, S. Thompson, Q. Zhang, Z. Zeng, S. Liu, P. Wang, Z. Guo, M. Tsukada. “Learning Diffusion Planners from World Feedback: A No-Go Result on Bit-Exact Safety Rewards and an ODD-Adaptive Shared/Expert Decomposition.” Workshop on Reinforcement Learning from World Feedback (RLxF), ICML 2026, Seoul, South Korea.
  6. Yun Li, S. Thompson, A. Orsholits, 塚田学. “正則化付き多重選好学習による自動運転 VLA モデルの安全制約アライメント.” 人工知能学会全国大会 (JSAI 2026), 群馬, Japan.
  7. Yun Li, Y. Chang, K. Fukawa, N. Kodama. “Reinforcement Learning-Based Cognitive Radio Transmission Scheduling in Vehicular Systems.” IEEE 97th Vehicular Technology Conference (VTC-Spring), 2023.

Refereed journal articles (with supervisor Rui Zhao)

  1. R. Zhao, Yun Li (lead student author), K. Wang, Y. Fan, F. Gao, Z. Gao. “Centralized Cooperation for Connected Autonomous Vehicles at Intersections by Safe Deep Reinforcement Learning.” IEEE Transactions on Mobile Computing, 2025. [IF = 7.9, CCF A]
  2. R. Zhao, Yun Li (lead student author), Y. Fan, F. Gao, M. Tsukada, Z. Gao. “A Survey on Recent Advancements in Autonomous Driving Using Deep Reinforcement Learning: Applications, Challenges, and Solutions.” IEEE Transactions on Intelligent Transportation Systems, 2024. [IF = 7.9, CCF A]
  3. R. Zhao, K. Wang, Yun Li, Y. Fan, F. Gao, Z. Gao. “Safe Multi-Agent Deep Reinforcement Learning for the Management of Autonomous Connected Vehicles at Future Intersections.” IEEE Transactions on Parallel and Distributed Systems, 2024. [IF = 5.6, CCF A]
  4. R. Zhao, Yun Li (lead student author), F. Gao, Z. Gao, T. Zhang. “Multi-Agent Constrained Policy Optimization for Conflict-Free Management of Connected Autonomous Vehicles at Unsignalized Intersections.” IEEE Transactions on Intelligent Transportation Systems, 2023. [IF = 7.9, CCF A]
  5. R. Zhao, Y. Fan, Yun Li, K. Wang, C. Zheng, F. Gao, Z. Gao. “Autonomous Intersection Management via Prior-Enhanced Multi-Agent Constrained Decision Transformer.” IEEE Transactions on Intelligent Transportation Systems, 2025. [IF = 8.5, Q1]
  6. R. Zhao, K. Wang, Yun Li, Y. Fan, F. Gao, Z. Gao. “Centralized cooperative control for autonomous vehicles at unsignalized all-directional intersections: A multi-agent projection-based constrained policy optimization approach.” Expert Systems with Applications, 2023. [IF = 8.5, Q1]
  7. R. Zhao, Q. Yuan, J. Li, H. Hu, Yun Li, Z. Gao, F. Gao. “Sce2DriveX: A generalized MLLM framework for scene-to-drive learning.” IEEE Robotics and Automation Letters, 2024. [IF = 5.2, Q1]
  8. R. Zhao, Yun Li (lead student author), H. Hu, Z. Gao. “Vehicle Collision Warning Method at Intersection Based on V2I Communication.” Journal of Jilin University, 2024.
  9. Additional co-author articles in Sensors (2024–2025), incl. DriveLLaVA, Cockpit-Llama, Knowledge-Distillation-Enhanced Behavior Transformer, Sequence Decision Transformer, Constraint-Guided Behavior Transformer, Intelligent Cockpits taxonomy, Adaptive Cruise Control via Safe DRL, and robust highway-driving via safe RL.

Patent

  • Yun Li, R. Zhao, Z. Gao. “Conflict-free cooperation method for self-driving vehicles at intersections based on deep reinforcement learning.” China Patent CN115457782A, 2023.

Invited talks

  1. “Preference-Guided LLMs for Driving Assistance.” 1st Workshop on Secure, Privacy-Aware Naturalistic Driving Data (SPADE) at IEEE IV 2025, Cluj-Napoca, Romania. Invited talk + panel.
  2. “Foundation Models for Autonomous Driving.” 1st Workshop on Foundation Models for Autonomous Driving (FMAD) at IEEE ITSC 2024, Edmonton, Canada.
  3. “Large Language and Vision Models for Autonomous Driving.” 2nd Workshop on LLVM-AD at IEEE ITSC 2024, Edmonton, Canada.
  4. “Vision Language Model based Human-Centered Autonomous Driving.” 1st Workshop on VLM-based Human-Centered Autonomous Driving at IEEE ITSC 2024, Edmonton, Canada.

Professional service

Peer reviewer for the following venues; records on Web of Science ResearcherID PEV-4339-2025.

  • Journals: IEEE T-ITS, IEEE TVT, IEEE IoTJ, Neurocomputing, Results in Engineering.
  • Conferences: IEEE IV, IEEE ITSC, IEEE/RSJ IROS.

Technical skills

  • Core research: World models, LLM model alignment, safe RL, autonomous driving, diffusion models.
  • Programming: Python (expert, 5+ years), C++ (advanced, 3+ years), MATLAB.
  • Frameworks: PyTorch, JAX, ROS 2, Autoware, AWSIM, nuPlan, CARLA, Docker, Linux, ONNX / TensorRT.
  • Languages: English (professional), Japanese (native-level), Chinese (native).