Maohua Li

I'm a master's student at Nanjing University in Suzhou, China. I am fortunate to be supervised by Prof. Shao-Qun Zhang at LAMDA. Before that, I obtained my bachelor's degree from Hohai University.

Email / Scholar / GitHub

Experience

Alibaba Group Holding

2025.12 - Now

AI-Engine, RTP-Compression

Research intern concentrating on visual generation, supervised by Dr. Hanlin Tang.

Peking University

2023.12 - 2025.05

School of Computer Science

Research intern concentrating on spiking neural networks, supervised by Prof. Zhaofei Yu.

4Paradigm

2024.10 - 2025.05

Department of Science and Technology

AI engineering intern. Ranked 1/400+ among all full-time employees and interns in Dec. 2024 and Jan. 2025.

Research

My research focuses on visual generative models. Especially:

Distillation
Representation
Interpretability

Previously, I was also interested in Spiking Neural Networks.

Projects

Wuli Qwen-Image Turbo

The State-of-the-Art distillation of Qwen-Image, delivering top-tier image quality with highly efficient inference. Featured on the Hugging Face homepage.

[Open-source weights: 2-step, 4-step] [Blog (量子位)]

ComfyUI Officially Adopted

Core Member

Publications

	SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation Yanjin He, Cuifeng Shen, Wanzhou Lei, Maohua Li, Tao Lan, Kan Liu, Hanlin Tang, Qing Qu arXiv
	Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate Wanzhou Lei, Cuifeng Shen, Yanjin He, Maohua Li, Hua Yuan, Per-Olof Persson, Tao Lan, Kan Liu, Hanlin Tang arXiv
	Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation Chenxi Xia, Yixuan Xu, Shan Liu, Jiapeng Wang, Maohua Li, Hanlin Tang, Kan Liu, Tao Lan, Weiyi Lu, Xinggao Liu arXiv
	Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Maohua Li, Qirui Li, Yanke Zhou, Yiduo Li, Zhaosheng Chi, Chao Xu, Cuifeng Shen, Yixuan Xu, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Shao-Qun Zhang arXiv 🤗 #3 Paper of the day
	Rethinking Cross-Layer Information Routing in Diffusion Transformers Chao Xu, Maohua Li, Qirui Li, Yixuan Xu, Yanke Zhou, Yunhe Li, Cuifeng Shen, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Shao-Qun Zhang NeurIPS 2026The Fortieth Annual Conference on Neural Information Processing Systems 🤗 #2 Paper of the day Blog (阿里技术)
	Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps Yanke Zhou, Yiduo Li, Hanlin Tang, Maohua Li, Kan Liu, Lan Tao, Lin Qu, Yuan Yao, Xiaoxing Ma NeurIPS 2026The Fortieth Annual Conference on Neural Information Processing Systems Blog (青稞AI)
	Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications Tong Bu, Maohua Li, Zhaofei Yu CVPR 2025Proceedings of the Computer Vision and Pattern Recognition Conference
	GC-SALM: Multi-Task Runoff Prediction Using Spatial-Temporal Attention Graph Convolution Networks Jin Lu, Zaipeng Xie, Jiayu Chen, Maohua Li, Chenghong Xu, Hongli Cao SMC 2023IEEE International Conference on Systems, Man, and Cybernetics

Academic Services

Reviewer

NeurIPS 2025, 2026
IEEE SMC 2023
Neurocomputing

This website is forked from jonbarron's web.