Yuecheng Liu (刘悦丞) — Home

I am Yuecheng Liu (刘悦丞), a researcher at Tongyi Lab, Alibaba Group. My research focuses on Agentic Reinforcement Learning, post-training of multimodal and full-modal foundation models, reinforcement learning and imitation learning algorithms and theories, as well as embodied intelligence, decision-making and control.

Contact

• Email: liuy150617@163.com (preferred), liuyuecheng.lyc@alibaba-inc.com, hitliuyc@gmail.com, liuyuecheng1@huawei.com (no longer in use)

Work Experience

• 2026.01 - Present: Tongyi Lab, Alibaba Group
  • Multimodal Large Language Model Research
• 2022.03 - 2025.12: Senior Researcher, Huawei Noah’s Ark Lab
  • Multimodal LLMs for Embodied AI
  • Spatial Reasoning and Planning
  • Large-scale Navigation Algorithms
  • Imitation Learning & Reinforcement Learning for Autonomous Driving
• 2021.05 - 2021.09: Research Intern, Tencent IEG
  • Reinforcement Learning for Game AI
• 2020.08 - 2021.04: Research Intern, Baidu NLP Department
  • Reinforcement Learning & Distributed RL Algorithms
  • Black-box Optimization for Smart Grid Control

Education

• 2019.09 - 2022.03: Master’s, Harbin Institute of Technology
• 2015.09 - 2019.06: Bachelor’s, Central South University

Research Interests

My research lies at the intersection of AI and Robotics, focusing on:

• Embodied AI: Building agents that perceive, reason, and interact with physical environments
• Reinforcement Learning: Algorithms for sequential decision-making and optimal control
• Multimodal Large Language Models: Cross-modal understanding, reasoning and modeling