I'm Yuheng Wu, an M.S. student in Electrical Engineering at Stanford University, advised by Prof. Thierry Tambe. 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.
AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
Hojoon Kim, Yuheng Wu, and Thierry Tambe
in Proceedings of the Conference on Machine Learning and Systems (MLSys), 2026.
RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
Yuzong Chen*, Xilai Dai*, Jake Hyun*, Chi-Chih Chang, Wonsuk Jang, Yuheng Wu, Thierry Tambe, Jae-sun Seo, and Mohamed S. Abdelfattah
Preprint.
LLM-FSM: Scaling LLMs for Finite-State Reasoning in RTL Code Generation
Yuheng Wu, Berk Gokmen, Zhouhua Xie, Peijing Li, Caroline Trippel, Priyanka Raina, and Thierry Tambe
Preprint.
P3-LLM: An Integrated NPU-PIM Accelerator for LLM Inference Using Hybrid Numerical Formats
Yuzong Chen, Chao Fang, Xilai Dai, Yuheng Wu, Thierry Tambe, Marian Verhelst, and Mohamed S. Abdelfattah
Preprint.
code
On the Role of Temperature Sampling in Test-Time Scaling
Yuheng Wu, Azalia Mirhoseini, and Thierry Tambe
ER and FoRLM Workshop @ NeurIPS 2025.
DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
Yuheng Wu, Jianwen Xie, Denghui Zhang, and Zhaozhuo Xu
in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 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, and Alex Aiken
in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 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, and Alex Aiken
in Proceedings of the Conference on Language Modeling (COLM), 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, and Denghui Zhang
Nature Partner Journals on Artificial Intelligence.
code
I enjoy playing tennis and watching films. My favorite tennis player is Carlos Alcaraz. Some of my favorite films include: