Minghui Hu

胡明辉

I received my PhD degree from Nanyang Technological University in Singapore, advised by Prof. P. N. Suganthan. Previousely, I received my MSc. degree in Electric and Electrical Engineering from NTU in 2019. Parallel to my doctoral studies, I hold a position as a researcher at Temasek Lab @ NTU, under the supervision of Dr. Sirajudeen s/o Gulam Razul.

I've had the distinct privilege of collaborating with Prof. T.J.Cham and Prof. Dacheng Tao from NTU, Dr. Chuanxia Zheng from VGG, University of Oxford and Dr. Chaoyue Wang from University of Sydney. I also had memorable experiences as a research intern Sensetime Research, JD Explore Academy and MiniMax.

Email / Google Scholar / Github / LinkedIn

News

[2024.06] GCS, a project with Zongrui, is accepted by ECCV2024.
[2024.02] MMoT is accepted by IJCV. Congrats Jianbin.
[2024.02] OneMoreStep is accepted by CVPR2024.
[2023.11] An ICONIP2023 submission wins the Best Student Award. Congrats Ruilin.
[2023.09] Cocktail🍸 is accepted by NeurIPS2023.
[2023.08] Self-Distillation for Randomized Neural Networks is accepted by T-NNLS.
[2023.07] SE(2)LiO is accepted by RA-L and presented at IROS2023. Congrats Jiaying Chen.
[2023.01] UniD3 is accepted by ICLR2023.
[2022.03] VQ-DDM is accepted by CVPR2022.

Research

My research focuses on generative models, multi-modality learning, and its applications in many domains, particularly 2D Image Generation. Prior to this, I was working on a network model with a simple topology named randomized neural networks.

	Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation Zongrui Li , Minghui Hu , Qian Zheng, Xudong Jiang, ECCV, 2024 project page / arXiv / code We analyze current SDS-based text-to-3D generation methods and propose an improved version with a bright normalizing trick for Gaussian Splatting. * equal contribution
	Trajectory Consistency Distillation Jianbin Zheng , Minghui Hu , Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao, Tat-Jen Cham Tech Report, 2024 project page / arXiv / code / HF Model / HF Space We distill a consistency model based on diffusion trajectory to improve the sample quality. * equal contribution
	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, 2024 project page / arXiv / code / HF Model / HF Space We develop a versatile plug-and-play module to fix the scheduler flaws for diffusion models.
	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, 2023 project page / arXiv / code / HF Model We develop a generalized HypreNetwork for multi-modality control based on text-to-image generative model.
	Self-Distillation for Randomized Neural Networks Minghui Hu, Ruobin Gao, P.N.Suganthan, T-NNLS IEEE / Code We integrate self-distillation into the randomized neural network to improve the generalization performance.
	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, IJCV project page / arXiv We introduce a Mixture-of-Modality-Tokens Transformer (MMoT) that adaptively fuses fine-grained multimodal control signals for multi-modality image generation.
	Versatile LiDAR-Inertial Odometry with SE(2) Constraints for Ground Vehicles Jiaying Chen, Han Wang, Minghui Hu, P.N.Suganthan, RA-L & IROS, 2023 IEEE We propose a hybrid LiDAR-inertial SLAM framework that leverages both the on-board perception system and prior information such as motion dynamics to improve localization performance.
	Class-Incremental Learning on Multivariate Time Series Via Shape-Aligned Temporal Distillation Zhongzheng Qiao, Minghui Hu, Xudong Jiang, P.N.Suganthan, Ramasamy Savitha, ICASSP, 2023 IEEE We propose to exploit Soft-Dynamic Time Warping (Soft-DTW) for knowledge distillation, which aligns the feature maps along the temporal dimension before calculating the discrepancy.
	Unified Discrete Diffusion for Simultaneous Vision-Language Generation Minghui Hu, Chuanxia Zheng, Zuopeng Yang, Tat-Jen Cham, Chaoyue Wang, Zuopeng Yang, Dacheng Tao, P.N.Suganthan ICLR, 2023 project page / arXiv / PDF We construct a unified discrete diffusion model for simultaneous vision-language generation.
	Representation Learning Using Deep Random Vector Functional Link Networks for Clustering Minghui Hu, P.N.Suganthan PR Elsevier We use manifold regularisation to learn the representation from the randomised networks.
	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, 2022 arXiv / PDF Instead of AutoRegresive Transformers, we use Discrete Diffusion Model to obtain a better global context for image generation.