Zhizhou Sha

I'm a final-year undergraduate majoring Computer Science and Technology, at Department of Computer Science and Technonlogy, Tsinghua University. Currently, I am a Research Intern, working with Zhao Song and Yingyu Liang.

Previously, I was fortunate to work with Zhuowen Tu at UCSD, for generative models in computer vision.

I really like to dicuss anything about research, life, and ourselves. Feel free to drop me an email!

I am actively looking for research opportunities and a Ph.D. position in 2025 Fall! Feel free to drop me an email if you think I will be a good fit.

Email / CV / Github / Linkedin / Google Scholar

Research

I am generally interested in enhancing the capabilities of multi-modality models, especially the generative models, and I am dedicated to understanding the theoretical foundations under contemporary Large Language Models.

Publications

	TokenCompose: Text-to-Image Diffusion with Token-level Supervision Zirui Wang, Zhizhou Sha, Zheng Ding, Yilin Wang, Zhuowen Tu CVPR 2024 paper / code / website
	OmniControlNet: Dual-stage Integration for Conditional Image Generation Yilin Wang, Haiyang Xu, Xiang Zhang, Zeyuan Chen, Zhizhou Sha, Zirui Wang, Zhuowen Tu GCV Workshop @ CVPR 2024 paper
	Dolfin: Diffusion Layout Transformers without Autoencoder Yilin Wang, Zeyuan Chen, Liangjun Zhong, Zheng Ding, Zhizhou Sha, Zhuowen Tu ECCV 2024 paper
	Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time (Alphabetical Order) Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou OPT Workshop @ NeurIPS 2024 paper
	Differential Privacy Mechanisms in Neural Tangent Kernel Regression (Alphabetical Order) Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song WACV 2025 paper
	Looped ReLU MLPs May Be All You Need as Programmable Computers (Alphabetical Order) Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou Under review paper
	HSR-Enhanced Sparse Attention Acceleration (Alphabetical Order) Bo Chen, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou Under review paper

This is the source code from Jon Barron. Thanks to him for sharing this beautiful template!