Yuheng Wu

I'm Yuheng Wu, an M.S. student in Electrical Engineering at Stanford University, advised by Prof. Thierry Tambe. At Stanford, I'm also fortunate to collaborate with Prof. Alex Aiken, Prof. Azalia Mirhoseini, and Prof. Sanmi Koyejo. Before joining Stanford, I received my B.E. in Electronic Information Engineering from Wuhan University.

My research centers on large language models (LLMs), with a focus on reasoning, test-time methods, verification, formal methods, and hardware-software co-design.

Email / CV / Scholar / Github

Research

LLM-FSM: Scaling LLMs for Finite-State Reasoning in RTL Code Generation
Yuheng Wu, Berk Gokmen, Zhouhua Xie, Peijing Li, Caroline Trippel, Priyanka Raina, Thierry Tambe
Preprint
P3-LLM: An Integrated NPU-PIM Accelerator for LLM Inference Using Hybrid Numerical Formats
Yuzong Chen, Chao Feng, Xilai Dai, Yuheng Wu, Thierry Tambe, Marian Verhelst, Mohamed Abdelfattah
Preprint
code
On the Role of Temperature Sampling in Test-Time Scaling
Yuheng Wu, Azalia Mirhoseini, Thierry Tambe
Preprint
ER and FoRLM Workshop @ NeurIPS 2025, San Diego, California, December 2025
DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
Yuheng Wu, Jianwen Xie, Denghui Zhang, Zhaozhuo Xu
in Proceedings of the Conference on Empirical Methods in Natural Language Processing
EMNLP 2025, Suzhou, China, November 2025
code / dataset / model
SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
Anjiang Wei*, Yuheng Wu*, Yingjia Wan, Tarun Suresh, Huanmi Tan, Zhanke Zhou, Sanmi Koyejo, Ke Wang, Alex Aiken
in Proceedings of the Conference on Empirical Methods in Natural Language Processing
EMNLP 2025, Suzhou, China, November 2025
code / dataset / website
CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
Anjiang Wei, Tarun Suresh, Jiannan Cao, Naveen Kannan, Yuheng Wu, Kai Yan, Thiago S. F. X. Teixeira, Ke Wang, Alex Aiken
in Proceedings of the Conference on Language Modeling
COLM 2025, Montreal, Canada, October 2025
code / dataset / website
How Large Language Models Encode Theory-of-Mind: A Study on Sparse Parameter Patterns
Yuheng Wu, Wentao Guo, Zirui Liu, Heng Ji, Zhaozhuo Xu, Denghui Zhang
Nature Partner Journals on Artificial Intelligence
code
Unmixing before Fusion: A Generalized Paradigm for Multi-Source-Based Hyperspectral Image Synthesis
Yang Yu*, Erting Pan*, Xinya Wang, Yuheng Wu, Xiaoguang Mei, Jiayi Ma
in Proceedings of the Conference on Computer Vision and Pattern Recognition
CVPR 2024, Seattle, Washington, June 2024
code / website

Service

Reviewer: CVPR 2026, ICLR 2026, NeurIPS 2025, IEEE Transactions on Image Processing, Journal of Artificial Intelligence Research, IEEE Transactions on Neural Networks and Learning Systems, Pattern Recognition

Miscellanea

I enjoy playing tennis and watching films. My favorite tennis player is Carlos Alcaraz. Some of my favorite films include:

(Click titles with links for more information.)

Blow-Up by Michelangelo Antonioni
Week-End by Jean-Luc Godard
Tropical Malady by Apichatpong Weerasethakul
Zama by Lucrecia Martel
Meek’s Cutoff by Kelly Reichardt
The Chronicle of Anna Magdalena Bach by Danièle Huillet and Jean-Marie Straub
Pacifiction by Albert Serra
Trenque Lauquen by Laura Citarella
Cyclo by Tran Anh Hung
Goodbye, Dragon Inn by Tsai Ming-Liang

Template taken from Jon Barron.