Minghui Hu

Researcher at SpellBrush, focusing on visual generative models.

Core contributor of niji journey and Midjourney models.

Previously: Sensetime, MiniMax

PhD from Nanyang Technological University, supervised by Prof. P. N. Suganthan and Prof. Tat-Jen Cham.

Scholar GitHub LinkedIn

Academic Services

Conferences
CVPR (2022–26, Outstanding Reviewer 2025) · ICCV (2023, 2025) · ECCV (2024, 2026) · NeurIPS (2023–26) · ICLR (2023–26) · ICML (2025-26) · etc.
Journals
T-PAMI · T-NNLS · T-Cyb · IJCV · Pattern Recognition · etc.
View Publications ↓
  1. Monocular Normal Estimation via Shading Sequence Estimation
    Zongrui Li, Xinhua Ma, Minghui Hu, Yunqing Zhao, Yingchen Yu, Qian Zheng, Chang Liu, Xudong Jiang, Song Bai
    ICLR 2026 (Oral)OpenReview
  2. Incremental online learning of randomized neural network with forward regularization
    Junda Wang, Minghui Hu, Ning Li, Abdulaziz Al-Ali, P.N. Suganthan
    IEEE T-PAMI
  3. Semantix: An Energy-guided Sampler for Semantic Style Transfer
    Huiang He*, Minghui Hu*, Chuanxia Zheng, Chaoyue Wang, Tat-Jen Cham
    ICLR 2025OpenReview
  4. Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation
    Zongrui Li*, Minghui Hu*, Qian Zheng, Xudong Jiang
    ECCV 2024ProjectarXivCode
  5. Trajectory Consistency Distillation
    Jianbin Zheng*, Minghui Hu*, Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao, Tat-Jen Cham
    Tech Report 2024ProjectarXivCodeModelDemo
  6. One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls
    Minghui Hu, Jianbin Zheng, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham
    CVPR 2024ProjectarXivCodeModelDemo
  7. Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
    Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham
    NeurIPS 2023ProjectarXivCodeModel
  8. Self-Distillation for Randomized Neural Networks
    Minghui Hu, Ruobin Gao, P.N. Suganthan
    IEEE T-NNLSIEEECode
  9. MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
    Jianbin Zheng, Daqing Liu, Chaoyue Wang, Minghui Hu, Zuopeng Yang, Changxing Ding, Dacheng Tao
    IJCVProjectarXiv
  10. Versatile LiDAR-Inertial Odometry with SE(2) Constraints for Ground Vehicles
    Jiaying Chen, Han Wang, Minghui Hu, P.N. Suganthan
    RA-L & IROS 2023IEEE
  11. Class-Incremental Learning on Multivariate Time Series Via Shape-Aligned Temporal Distillation
    Zhongzheng Qiao, Minghui Hu, Xudong Jiang, P.N. Suganthan, Ramasamy Savitha
    ICASSP 2023IEEE
  12. Unified Discrete Diffusion for Simultaneous Vision-Language Generation
    Minghui Hu, Chuanxia Zheng, Zuopeng Yang, Tat-Jen Cham, Chaoyue Wang, Dacheng Tao, P.N. Suganthan
    ICLR 2023ProjectarXiv
  13. Representation Learning Using Deep Random Vector Functional Link Networks for Clustering
    Minghui Hu, P.N. Suganthan
    Pattern RecognitionElsevier
  14. Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation
    Minghui Hu, Yujie Wang, Tat-Jen Cham, Jianfei Yang, P.N. Suganthan
    CVPR 2022arXiv