CS PhD Student @ DukeI am a 1st year CS PhD student at Duke University.
I study the foundations of advanced AI models, focusing on how and why they work.
My current research centers on understanding how and why advanced AI models—such as large language models and diffusion models—work, and on leveraging this understanding to make them more accurate, efficient, and robust. More broadly, I am interested in AI across theoretical, empirical, and even philosophical dimensions, as well as in areas where stronger foundations may unlock exciting applications, from trustworthy AI to agentic intelligence and AI for science.
I am always open to discussions. Feel free to reach out.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Duke UniversityPh.D. in Computer ScienceAug. 2025 – Present
-
University of PennsylvaniaM.S.E. in Scientific ComputingAug. 2023 - May. 2025 -
Wuhan UniversityB.E. in Engineering MechanicsSep. 2019 - Jul. 2023
News
Selected Publications (view all )
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Yufa Zhou (alphabetical order)
ICCV 2025
We provide a theoretical analysis showing that for diffusion models with Gaussian mixture data, the diffusion process preserves the mixture structure; we derive tight, component-independent bounds on Lipschitz constants and second moments, and establish error guarantees for diffusion solvers—offering deeper insights into the diffusion dynamics under common data distributions.
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Yufa Zhou (alphabetical order)
ICCV 2025
We provide a theoretical analysis showing that for diffusion models with Gaussian mixture data, the diffusion process preserves the mixture structure; we derive tight, component-independent bounds on Lipschitz constants and second moments, and establish error guarantees for diffusion solvers—offering deeper insights into the diffusion dynamics under common data distributions.
Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Yufa Zhou*, Shaobo Wang*, Xingyu Dong*, Xiangqi Jin, Yifang Chen, Yue Min, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang (* equal contribution)
arXiv 2025
We investigate whether post-training techniques such as SFT and RLVR can generalize to multi-agent systems, and introduce Recon—a 7B model trained on a curated dataset of economic reasoning problems—which achieves strong benchmark performance and exhibits emergent strategic generalization in multi-agent games.
Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Yufa Zhou*, Shaobo Wang*, Xingyu Dong*, Xiangqi Jin, Yifang Chen, Yue Min, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang (* equal contribution)
arXiv 2025
We investigate whether post-training techniques such as SFT and RLVR can generalize to multi-agent systems, and introduce Recon—a 7B model trained on a curated dataset of economic reasoning problems—which achieves strong benchmark performance and exhibits emergent strategic generalization in multi-agent games.
Looped relu mlps may be all you need as practical programmable computers
Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou (alphabetical order)
AISTATS 2025
We demonstrate that a looped 23-layer ReLU-MLP can function as a universal programmable computer—revealing that simple neural network modules possess greater expressive power than previously thought and can perform complex tasks without relying on advanced architectures like Transformers.
Looped relu mlps may be all you need as practical programmable computers
Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou (alphabetical order)
AISTATS 2025
We demonstrate that a looped 23-layer ReLU-MLP can function as a universal programmable computer—revealing that simple neural network modules possess greater expressive power than previously thought and can perform complex tasks without relying on advanced architectures like Transformers.
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou (alphabetical order)
ICLR 2025
We introduce a novel LLM weight pruning method that directly optimizes for approximating the non-linear attention matrix—with theoretical convergence guarantees—effectively reducing computational costs while maintaining model performance.
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou (alphabetical order)
ICLR 2025
We introduce a novel LLM weight pruning method that directly optimizes for approximating the non-linear attention matrix—with theoretical convergence guarantees—effectively reducing computational costs while maintaining model performance.
All publications
Academic Services
-
Conference Reviewer: ICLR 2025, NAACL 2025, IJCAI 2025, ACL 2025, EMNLP 2025, AAAI 2026.
-
Journal Reviewer: TKDE, TNNLS.