Background & experience

Curriculum vitae

Research Engineer in Robotics at Shanghai AI Laboratory, seeking PhD opportunities in robot learning and embodied AI. My research interests include offline reinforcement learning, agentic reinforcement learning, embodied agents, and robotic manipulation.

Education

Shanghai Jiao Tong University Sep 2023 – Apr 2026

M.Sc., Control Science and Engineering
Machine Vision and Autonomous System Laboratory · Advisor: Prof. Jun-Guo Lu
GPA: 3.89/4.0 · Outstanding Graduate (2026)

Shanghai Jiao Tong University Sep 2019 – Jun 2023

B.Eng., Automation · Zhiyuan Honors Program
Minor in Economics, Antai College of Economics and Management
Major GPA: 3.69/4.0 · Outstanding Graduate of Shanghai Jiao Tong University

Research & engineering experience

Shanghai AI Laboratory Nov 2025 – Present

Research Engineer, Robotics

  • Research in reinforcement learning, embodied agents, and robotic manipulation.
  • Shared first author of REAL (ECCV 2026), InfCoiL (NeurIPS 2026), PICA-WAM, and the EBench frontier-agent evaluation report; coauthor of the InternW0 series of technical reports.

Turin Robotics / Shanghai Baosight Software Oct 2024 – Oct 2025

Project collaboration

  • Developed reinforcement learning and imitation learning algorithms for humanoid robots.

Machine Vision and Autonomous System Laboratory, SJTU

Graduate research · Advisor: Prof. Jun-Guo Lu

  • Developed GBC, an open-source framework for motion retargeting and whole-body humanoid imitation.
  • Developed AnyBipe, integrating language-guided reward design, robot training, and sim-to-real evaluation.

Earlier engineering experience

  • LIMX Dynamics collaboration (Jun – Oct 2024): bipedal robot testing and locomotion research.
  • ZIDAI industrial collaboration (Nov 2023 – Jun 2024): bird’s-eye-view perception, semantic segmentation, and distance estimation for maritime applications.
  • SAIC Motor AI Research Institute (Jun – Nov 2023): Android and OpenGL development for vehicle surround-view systems.
  • Shanghai University of Sport collaboration (Nov 2022 – Jun 2023): human pose estimation and motion-sequence analysis.

Publications

Complete records, code links, and citations are on the publications page.

Conference Papers

NeurIPS 20262026 · AcceptedCo-first author

InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction

Yude Zou*, Yifei Yao*, Yiwei Hao*, Hanqing Wang, Xing Gao

* Equal contribution (co-first authors).

Make generated motion executable. InfCoiL lets a flow-matching planner and a physics-based controller improve each other through shared rollout feedback, alternating their RL updates when progress plateaus.

My contribution: I designed and implemented the RL training, including SFPO for the flow-matching planner and plateau-triggered coordinated updates of the planner and controller.

ECCV 20262026Co-first author

Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

Boyu Mi*, Mengchen Ma*, Yifei Yao*, Xing Gao, Junting Chen, Yangzi Li, Zihou Zhu, Guohao Li, Zhenfei Yin, Tai Wang, Yao Mu, Jiangmiao Pang, Hanqing Wang

* Equal contribution (co-first authors).

Vision-driven mobile manipulation through active exploration, visual grounding, and interactive intent disambiguation, with a shared interface for simulation and real robots.

My contribution: I built the RL environments, designed rewards, trained the RL policies, and designed and annotated task trajectories.

Preprints

SSRN2026

Length-Adaptive PPO-based RLHF for Non-Uniform UAV Control

Fuwei Tan, Zhen Zhu, Yifei Yao, Qing-Hao Zhang, Xiaodong Han, Junguo Lu

Length-adaptive proximal policy optimization with reinforcement learning from human feedback for non-uniform UAV control.

My contribution: I contributed to the discussion and improvement of the RL approach.

Technical Reports

Ongoing Research

Research project2026 · In progress

Learning Embodied Agents from Experience

How can an open model learn to act from a frontier agent’s experience? I am studying the transfer of Astra’s robot interaction experience to Qwen3.8-27B through staged SFT and reinforcement learning, connecting visual grounding, short manipulation skills, and long-horizon tasks.

Research project2026 · In development

ARIEL: An Agent-Ready Humanoid Behavior Model with In-Context Execution Memory

ARIEL gives an agent a simple interface to whole-body control. Choose a demonstration, load it into memory, then recall the motion or steer its style with velocity and heading commands. The controller keeps executing between agent decisions.

My contribution: I am developing ARIEL as a continuation of my work on humanoid controllers.

Preprint2026 · arXiv release pendingCo-first author

Review the Episodes, Refine the Lessons: Simple Memory Evolution for Embodied Agents

Yifei Yao*, Yude Zou*, Guanbo Jiao, Yukai Wang, Jianming Ma, Xing Gao, Weinan Zhang, Chunhua Shen

* Equal contribution (co-first authors).

An embodied agent learns from execution experience by refining text memory across training episodes, then uses frozen memory at evaluation without updating model weights.

My contribution: I designed the experiments, refined the framework, and discussed the results.

Manuscript2026 · Manuscript in preparation

ABI: Actor-Free Zero-Shot Reinforcement Learning with Behavior-Inductive Representations

Yifei Yao

First author; full author list to be finalized.

Given an existing policy, ABI trains only a reusable guide. The guide improves task execution at deployment while the policy stays frozen, with no parameter updates or task-specific policy post-training.

My contribution: I formulated the research problem, developed the method and theoretical analysis, implemented the system, designed and ran the experiments, and wrote the manuscript.

Technical skills

  • Programming: Python, C/C++, MATLAB, Java, Kotlin.
  • Learning & simulation: PyTorch, Isaac Lab, Isaac Sim, Isaac Gym, MuJoCo.
  • Robotics & systems: ROS/ROS2, OpenCV, OpenGL, Linux, Docker, Git.

Selected honors

Academic distinctions

  • Outstanding Graduate (Master’s) (2026)
    Shanghai Jiao Tong University
  • Outstanding Graduate (Bachelor’s) (2023)
    Shanghai Jiao Tong University

Competitions & presentations

  • Outstanding Winner, Mathematical Contest in Modeling (MCM/ICM) (2021)
    COMAP
  • National First Prize, RoboCup Robot World Cup China Competition (2022)
    Intelligent Vehicle Challenge · 2021 edition, awarded in June 2022
  • Third Prize, Mitsubishi Electric Cup National Electrical and Automation Competition (2021)
    Undergraduate Innovative Design track
  • Student Presentation Award (2023, 2024)
    China Association of Automation, Shanghai

Scholarships & student honors

  • Outstanding Scholarship (2025)
    Shanghai Jiao Tong University
  • Academic Scholarship, First Prize / Tier 1 (2024, 2025)
    Shanghai Jiao Tong University
  • Zhiyuan Honor Scholarship (2019–2023)
    Shanghai Jiao Tong University
  • Leadership Scholarship (2022)
    Shanghai Jiao Tong University
  • SEIEE Academic Scholarship (Class C) (2021–2022)
    Shanghai Jiao Tong University
  • Excellent Student Cadre (2021)
    Shanghai Jiao Tong University · 2020–2021 academic year

Contact

jameswhiteyao@gmail.com · Google Scholar · GitHub
Academic email: godchaser@sjtu.edu.cn