Zhenglin (Carlos) Wan

Zhenglin (Carlos) Wan

😊 About me

Contact: vanzl3386 [at] gmail.com (main), vanzl [at] u.nus.edu, 121090525 [at] link.cuhk.edu.cn

I am Zhenglin Wan (万政霖), a CS Ph.D. student at HPC-AI Lab at National University of Singapore (NUS), advised by Prof. Yang You. Previously, I worked at Nanyang Technological University (NTU) with Prof. Bo An, Centre for Frontier AI Research (CFAR), IHPC, A*STAR with Prof. Ivor Tsang , Hong Kong Generative AI Research & Development Center (HKGAI) with the team led by HKUST Prof. Yike Guo. I received my B.Sc (with 1-st class honor) in Statistics and Data Science from The Chinese University of Hong Kong (CUHK).

My research is driven by the curiosity of genuinely understanding (both theoretically and intuitively) the rationale, spirit and failure modes of ML algorithms and methods. Based on this principle, I am recently working on fundamental side of Multi-modal generation and RL Post-training. Particularly:

  • RL post-training on continuous-space generative models (such as diffusion model)
  • Unified AR-based understanding and Diffusion-based Generation and the RL-post-training paradigm of such systems
  • Long-horizon agents and unified model (Agentic unified model), such as Agentic VLA and Agentic Video Generation, and the RL-post-training paradigm

I love intellectual games in my spare time: I am a 17-years chess player as National Chess Athlete of China (Grade 3), and have won the 1-st prize in Chinese Mathematics Olympiad (CMO)-1st round by 1.5-year’s part-time self-training.

🔥 News

  • 2026.05  🎉 GoRL is accepted to ICML 2026, providing a new perspective for online RL training with diffusion/flow policy for robot learning. ([Paper], [Code])
  • 2026.05  🎉 OSCAR (training free method for diverse rollout of diffusion model) is accepted to ICML 2026. ([Paper], [Code]).
  • 2026.04  🎉🎉 Gave a talk invited by Meta MRS (topic: Stable online RL for alignment of diffusion-based foundation models).
  • 2026.01  🎉 Cave-Agent is open-sourced: an object-oriented coding agentic framework with superior token-efficiency, empowering the agentic AI system being built by the Hong Kong Government.
  • 2025.05  🎉🎉 EBC (Evolutionary Strategy for robot learning to learn diverse policies) is accepted by ICML 2025.
  • 2019.09  🎉🎉 Lucky to win the 1-st prize in Provincial Chinese Mathematics Olympiad (CMO). Thanks for this intellectually-rewarding experience.

📝 Selected Publications

Conference papers and Preprints

Please scroll down to view more. * denotes joint-first-author and equal contribution.

📖 Educations

  • Doctor of Philosophy (Ph.D)

    National University of Singapore (NUS)

    • Affiliation: Department of Computer Science, School of Computing
    • Advisor: Prof. Yang You

    NUS

  • Bachelor of Science (B.Sc)

    The Chinese University of Hong Kong (CUHK)

    • 1-st class honor
    • Major: Statistics & Data Science, GPA: 3.85/4.0, Rank: 7%
    • Completed my undergraduate in CUHK-Shenzhen campus, while the degree is offered by CUHK.

    CUHK(SZ)

💻 Internships and Work Experiences

  • Full-time Research Staff

    Nanyang Technological University, Singapore

    • Affiliation: College of Computing and Data Science (CCDS)
    • Advisor: Prof. Bo An

    NTU

  • Intern (Remote)

    Hong Kong Generative AI Research & Development Center (HKGAI), HKUST

    • Affiliation: HKGAI
    • Director: Prof. Yike Guo
    • Proposed a new product-inspired Agentic Function Calling paradigm ([[CaveAgent]]).

    HKGAI

  • Intern Researcher

    Agency for Science, Technology and Research (A*STAR), Singapore

    • Affiliation: Centre for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC)
    • Advisor: Prof. Ivor Tsang, Dr. Xingrui Yu

    A*STAR

  • Research Assistant

    The Chinese University of Hong Kong, Shenzhen

    • Affiliation: School of Data Science
    • Advisor: Prof. Jianfeng Mao

    CUHK(SZ)

🎤 Invited Talks

  • Object-Oriented Agent Infrastructure — Invited by Qingke AI Community
  • Stable Online Alignment of Diffusion-based Foundation Model — Invited by Meta (MRS)

🎈 Services

  • Reviewer of AAAI, ICLR, ICML, NeurIPS

🎖 Honors, Awards and Scholarships

  • NUS Research Scholarship (Ph.D stipend and tuition fee subsidy)

  • 1-st class honor undergraduate student awarded by The Chinese University of Hong Kong

  • Yearly Academic Scholarship: B Class (for GPA Top 3%, ￥40000)

  • Yearly Academic Scholarship: C Class (for GPA Top 5%, ￥20000)

  • Yearly Dean List Award (Outstanding 1-st class Performance, for 3 years)

  • Diligentia Bowen Scholarship (￥120000, Undergraduate Admission Scholarship for 1-st prize in Provincial CMO)

  • Zhejiang Guolong Inspirational Scholarship (￥120000, Undergraduate Admission Scholarship for top 0.5% students in Chinese College Entrance Exam)

  • 1st-Prize in Chinese Mathematics Olympiad (CMO)-1st round

💬 Press/Media

White Paper
sym

Miscellaneous

  • In my spare time, I’m an music enthusiast. I’ve been playing guitar for more than 10 years and began teaching myself the piano when I was 15. During my undergraduate, I played music in two bands: “Minor Blue” and “Major Pink.” See our photos:
sym sym sym

  • I am also a 17-years chess player, with the honor of “National Athlete”. I love the process of comprehensive planning, logical-thinking and reasoning. Visit my Lichess profile.

  • I play video games like League of Legends, where I achieved the “diamond” level as my historically highest honor. I also play 3A games like Elden Ring, Dark Souls, Nier Automata, and elder scrolls.

  • I have a deep interest in philosophy of mind, particularly Buddhism and Taoism, as paths to explore the fundamental nature of human existence. I am also intrigued by the potential integration of these philosophical insights with modern artificial intelligence.