Haonan Wang

Haonan Wang

王浩楠

Ph.D. Student in HKUST

Biography

I am a Ph.D. student supervised by Prof. Xiaomeng Li at The Hong Kong University of Science and Technology.

Before that, I received my Master’s degree from The University of Hong Kong and my B.Eng degree from Northeastern University supervised by Prof. Peng Cao.

Research interest:

  • Deep Learning
  • Computer Vision
  • Label-efficient Learning
  • Medical Image Analysis
  • Foundation Models
  • Brain Decoding
  • Generative Models


News

Static Badge   1 co-authored paper accepted by ICLR-2026.

Static Badge   1 paper accepted by NeurIPS-2025. We propose ZEBRA, the first zero-shot brain visual decoding framework that eliminates the need for subject-specific adaptation. 

Static Badge   2 papers accepted by ICCV-2025. (Neurons & TAM) TAM is selected as Oral Presentation!

Static Badge   1 co-authored paper accepted by TMI-2025.

Static Badge   1 co-authored paper accepted by ICLR-2025.

Static Badge   1 co-authored paper accepted by TMI-2024.

Static Badge   1 paper accepted by CVPR-2024.

Static Badge   1 paper accepted by NeurIPS-2023.

Static Badge   Join Prof. Xiaomeng Li’s lab at HKUST to pursue my Ph.D. degree.

Static Badge   1 paper accepted by MICCAI-2023.

Static Badge   1 paper accepted by AAAI-2022.


Publications

$^\dagger$ denotes equal contribution.

Brain Decoding Foundation Models / VLMs Label-efficient Learning Segmentation Interpretability All
Arxiv 2026
semkey

Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding GitHub Repo stars

Arxiv Preprints, 2026

Yuchen Wang, Haonan Wang, Yu Guo, Honglong Yang, Xiaomeng Li

   

ICLR 2026
vcflow

A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding

The Fourteenth International Conference on Learning Representations (ICLR), 2026

Jingyu Lu, Haonan Wang, Qixiang Zhang, Xiaomeng Li

NeurIPS 2025
ZEBRA

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding GitHub Repo stars

Advances in Neural Information Processing Systems (NeurIPS), 2025

Haonan Wang, Jingyu Lu, Hongrui Li, Xiaomeng Li

Arxiv 2025
UniEval

UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation GitHub Repo stars

Arxiv Preprints, 2025

Yi Li, Haonan Wang, Qixiang Zhang, Boyu Xiao, Chenchang Hu, Hualiang Wang, Xiaomeng Li

Website

ICCV 2025
Neurons

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction GitHub Repo stars

International Conference on Computer Vision (ICCV), 2025

Haonan Wang $^\dagger$, Qixiang Zhang $^\dagger$, Lehan Wang, Xuanqi Huang, Xiaomeng Li

ICCV 2025
TAM

Token Activation Map to Visually Explain Multimodal LLMs GitHub Repo stars

International Conference on Computer Vision (ICCV), 2025

🏅 Oral Presentation (oral rate: 64/11,239 = 0.57%)

Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, Xiaomeng Li

ICLR 2025
MedRegA

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks GitHub Repo stars

The Thirteenth International Conference on Learning Representations (ICLR), 2025

Lehan Wang, Haonan Wang, Honglong Yang, Jiaji Mao, Zehong Yang, Jun Shen, Xiaomeng Li

TMI 2025
SND

S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation GitHub Repo stars

IEEE Transactions on Medical Imaging (TMI), 2025

Qixiang Zhang $^\dagger$, Haonan Wang $^\dagger$, Xiaomeng Li

CVPR 2024
allspark

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation GitHub Repo stars

IEEE / CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Haonan Wang $^\dagger$, Qixiang Zhang $^\dagger$, Yi Li, Xiaomeng Li

NeurIPS 2023
AND

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation GitHub Repo stars

Advances in Neural Information Processing Systems (NeurIPS), 2023

Haonan Wang, Xiaomeng Li

MICCAI 2023
DHC

DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation GitHub Repo stars

Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023

Haonan Wang, Xiaomeng Li

AAAI 2022
UCTransNet

UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer GitHub Repo stars

36th AAAI Conference on Artificial Intelligence (AAAI), 2022

🏅 Top-1 Most Influential AAAI 2022 Paper

Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R. Zaiane

Full Publication List

For a complete list of publications, please refer to my Google Scholar.



Educations

  • 2023.09 -         Ph.D. student, HKUST.
  • 2022.09 - 2023.09   MSc, Computer Science, HKU.
  • 2017.09 - 2021.06   BEng, Computer Science, Northeastern University.


Professional Activities

Journal Reviews

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Image Processing (TIP)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Medical Imaging (TMI)
  • IEEE Journal of Biomedical and Health Informatics (JBHI)

Conference Reviews

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • International Conference on Computer Vision (ICCV)
  • International Conference on Machine Learning (ICML)
  • International Conference on Learning Representations (ICLR)
  • Conference on Neural Information Processing Systems (NeurIPS)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • Medical Image Computing and Computer-Assisted Intervention (MICCAI)