Hi there! I am Mingxiao Li and I am currently pursuing a PhD at KU Leuven under the guidance of Prof.Marie-Francine Moens. My current research focuses on Vision and Language, Generative Models and Large Vision Language Model. Feel free to contact me for questions and collaborations.

Before my PhD, I obtained my MSc. in Artificial Intelligence (2019) and Quantum Chemistry and Computational Modeling (2018) from KU Leuven, and my BSc. in Material Physics (2015) from East China University of Science and Technology (ECUST).

Selected Publications

• NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties.
  Jingyuan Sun *, Mingxiao Li *, Zijiao Chen, Marie-Francine Moens.
  Proceeding of the AAAI Conference on Artificial Intelligence (AAAI 2025)
  Paper Code

• Animate Your Motion: Turning Still Images into Dynamic Videos.
  Mingxiao Li *, Bo Wan *, Marie-Francine Moens, Tinne Tuytelaars.
  European Conference on Computer Vision (ECCV 2024)
  Paper Project Page Code

• Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps.
  Mingxiao Li *, Tingyu Qu *, Ruicong Yao, Wei Sun, Marie-Francine Moens.
  International Conference on Learning Representatons (ICLR 2024)
  Paper Code

• Elucidating the Exposure Bias in Diffusion Models.
  Mang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, Itir Onal Ertugrul
  International Conference on Learning Representatons (ICLR 2024)
  Paper Code

• Contrast, Attend and Diffuse to Decode High-Resolution Images fro Brain Activities.
  Jingyuan Sun *, Mingxiao Li *, Zijiao Chen, Yunhao Zhang, Shaonan Wang, Marie-Francine Moens.
  Advances on Neural Information Processing Systems (NeurIPS 2023)
  Paper Code

• Layout-Aware Dreamer for Embodied Visual Referring Expression Grounding.
  Mingxiao Li *, Zehao Wang *, Tinne Tuytelaars, Marie-Francine Moens.
  Proceeding of the AAAI Conference on Artificial Intelligence (AAAI 2023) Oral Presentation
  Paper Code

• Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering.
  Mingxiao Li, Marie-Francine Moens.
  Proceeding of the AAAI Conference on Artificial Intelligence (AAAI 2022)
  Paper Code

Preprint

• TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
  Tingyu Qu, Mingxiao Li, Tinne Tuytelaars, Marie-Francine Mones
  Paper Code ModelScopeCommunity

• Action-based image editing guided by human instructions
  Maria Mihaela Trusca, Mingxiao Li, Marie-Francine Moens
  Paper

• DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
  Mang Ning, Mingxiao Li *, Jianlin Su *, Haozhe Jia, Lanmiao Liu, Martin Beneš, Albert Ali Salah, Itir Onal Ertugrul
  Paper Code

(Note: * indicates equal contribution)

Service

Reviewer: ICML, CVPR, ICLR, NeurIPS, AAAI, EMNLP, ACL, ECAI, ECML, EACL
Workshop Organizer: AAAI-2024 Workshop: Artificial Intelligence for Brain Encoding and Decoding (AIBED)