Young Researcher · Shanghai AI Laboratory

Mingxiao Li

I work on generative and understanding models for AI for Science, with a continuing interest in visual generation and multimodal intelligence.

My current work at Shanghai AI Laboratory focuses on AI for Science discovery, with an emphasis on molecular generation, unified molecular tokenization, and reasoning models for scientific problems. In parallel, I continue to develop visual generation models for controllable video synthesis and multimodal understanding.

Before joining Shanghai AI Laboratory, I was a postdoctoral researcher at KU Leuven, where my research was guided by Prof. Marie-Francine Moens.

Portrait of Mingxiao Li
Shanghai, China

Research

I study how generative models can discover, represent, and reason about complex scientific and visual worlds.

Education

2025—

Young Researcher
Shanghai AI Laboratory · AI for Science Center

2024—25

Postdoctoral Researcher
Computer Science · KU Leuven

2019—24

PhD in Computer Science
KU Leuven · summa cum laude

2018—19

Master of Artificial Intelligence
KU Leuven

2016—18

Master of Theoretical Chemistry & Computational Modeling
KU Leuven

2011—15

Bachelor of Material Physics
East China University of Science and Technology

Selected publications

Full list on Google Scholar ↗
  1. NeurIPS 2025

    Consistent Story Generation: Unlocking the Potential of Zigzag Sampling. [Paper]

  2. ICML 2025

    DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space. [Paper]

  3. AAAI 2025 · Oral

    NeuroCine: Decoding Vivid Video Sequences from Human Brain Activities. [Paper]

  4. ECCV 2024

    Animate Your Motion: Turning Still Images into Dynamic Videos. [Paper]

  5. ICLR 2024

    Alleviating Exposure Bias in Diffusion Models through Shifted Time Steps. [Paper]

  6. NeurIPS 2023

    Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities. [Paper]

  7. ICLR 2024

    Elucidating the Exposure Bias in Diffusion Models. [Paper]

  8. AAAI 2023 · Oral

    Layout-Aware Dreamer for Embodied Visual Grounding. [Paper]

Technical notes

Open the notes archive ↗

I write about the techniques behind my work: diffusion, sampling, molecular representations, multimodal reasoning, and the practical craft of research engineering.

Writing studio Draft in Markdown, preview formulas and images, then export a note for publication. Open the private editor →

Service & awards

Academic service

Area Chair · ACL Rolling Review (2025.02)
Workshop organizer · AAAI 2024 AIBED

Reviewer for ICML, CVPR, ICLR, NeurIPS, AAAI, EMNLP, ACL, ECAI, ECML, and EACL.

Awards

Summa cum laude PhD
Erasmus Mundus Full Scholarship
Chinese Government Scholarship

Contact

I am always happy to hear about thoughtful questions, unusual ideas, and potential collaborations.

eric.lee.xiao@gmail.com
Page views
Visitors