CV

PDF Download

Education

• PhD in Computer Science - University of Cambridge
• MS in Aerospace Engineering - University of Arizona
• BS in Honors Computer Science - University of California, Santa Cruz

Work Experience

• University of Macau - Assistant Professor
• University of Cambridge - Adjunct Lecturer
• Anyscale - Contract Software Engineer (Reinforcement Learning)
• Toshiba Research Europe - Graduate Research Intern
• NASA Jet Propulsion Lab - Graduate Robotics Research Intern
• Meta - Production Engineer II

Skills

Core Competencies

• Deep Learning, Reinforcement Learning, Sequence Modeling, Multi-Agent Reinforcement Learning, Robotics

Models

• World Models, RNNs, Transformers, Generative Models, Variational Models

ML Frameworks

• JAX, PyTorch, Numpy, Equinox

Programming Languages

• Python

Software

• SolidWorks, Linux, ROS2, MATLAB, Git

Publications

• Investigating Memory in Model-Free RL with POPGym Arcade
• Explore to Learn: Latent Exploration through Disentangled Synergy Patterns for Reinforcement Learning in Overactuated Control
• Language-Conditioned Offline RL for Multi-Robot Navigation
• CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications
• Recurrent Reinforcement Learning with Memoroids
• Task Performing Agent Systems and Methods
• Reinforcement Learning with Fast and Forgetful Memory
• Generalised f-Mean Aggregation for Graph Neural Networks
• POPGym: Benchmarking Partially Observable Reinforcement Learning
• Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning
• A framework for real-world multi-robot systems running decentralized GNN-based policies
• Modeling Partially Observable Systems using Graph-Based Memory and Topological Priors
• Embodied Visual Navigation With Automatic Curriculum Learning in Real Environments
• Improving Visual Feature Extraction in Glacial Environments
• A Spring Propelled Extreme Environment Robot for Off-world Cave Exploration

Talks

Conferences & Workshops

• Panel: Memory in Reinforcement Learning
• Understanding and Benchmarking Memory in RL
• Value-Based Reinforcement Learning

Invited Talks

• Deep Reinforcement Learning with Memory
• Reinforcement Learning under Partial Observability
• An Introduction to Reinforcement Learning

Guest Lectures

• Deep Decision Making
• Reinforcement Learning with Memory

Teaching

Instructor

• Special Topics in AI — Decision Making and Reinforcement Learning
• Introduction to Deep Learning
• Special Topics in AI — Decision Making and Reinforcement Learning
• Introduction to Deep Learning
• Deep Reinforcement Learning

Teaching Assistant

• Programming in C/C++
• Introduction to Robotics
• Mobile Robot Systems

Thesis Supervision

• Yutao Chen, PhD, Deep Mixture Modeling with Natural Gradients, Macau (2025–)
• Xiaoming Liu, PhD, Offline Reinforcement Learning for Mobile Manipulation, Macau (2025–)
• Wang Zekang, MS, Evaluating and Rethinking Memory in RL, Macau (2024–2026)
• He Zhe, MS, Efficient Memory Diagnostic Benchmark and Parallelized RL, Macau (2024–2026)
• Dulhan Jayalath, MPhil, Reconstructing Markov States in Decentralised Multi-Agent RL, Cambridge (2022–2023)
• Mark Li, Part II, Intrinsically Go-Explore in Reinforcement Learning, Cambridge (2023–2024)
• James Read, Part II, Offworld SLAM, Cambridge (2021–2022)

Awards, Fellowships & Grants

• Funding Scheme for Research and Innovation (Co-Investigator) - Macau FDCT (2025)
• Enhancement Programme - University of Macau (2025)
• Startup Research Grant - University of Macau (2025)
• 2nd Best Research Talk - Jesus College Graduate Conference, University of Cambridge (2023)
• Graduate Research Studentship - Toshiba Research (2021)
• Cum Laude - University of California, Santa Cruz (2015)

Service and Outreach

• Director, AI and Robotics Summer School, University of Macau (2026)
• Session Chair, IEEE Big Data Conference, Macau (2025)
• Faculty Affiliate, Moon Chun Memorial College, University of Macau (2025–2026)
• PhD Defense Committee, Sun Binbin, University of Macau (2025–2026)
• MS Thesis Examination Chair, Huanrong Liu, University of Macau (2026)
• MS Thesis Examination Chair, Ting Huang, University of Macau (2026)
• MS Thesis Examination Chair, Zhijia Tao, University of Macau (2026)
• MS Thesis Examination Chair, Leandro Schlosser Acosta, University of Macau (2025)
• MS Project Examiner, Artificial Intelligence, University of Macau (2025, 2026)
• BS Thesis Examiner, Artificial Intelligence, University of Macau (2026)
• Mentor, UC Santa Cruz (2023)
• Volunteer, Boys and Girls Club, Tucson (2018)

Peer Review

• ICLR (2024–2026)
• ICML (2024–2026)
• NeurIPS (2024–2026)
• AAAI (2025)
• ICRA/RA-L (2020–2021)
• RSS (2024)
• CoRL (2026)