Shixuan Li (李诗轩)

Hi everyone! 👋 I am a 3rd-year Ph.D. student in Computer Engineering at the University of Southern California, advised by Prof. Paul Bogdan. I received my M.S. in Computer Engineering from USC (2025) and my B.E. in Computer Science from Huazhong University of Science and Technology (2023).

My research interests focus on Large Language Models (LLMs) and Multi-Agent Systems, including reasoning and collaboration mechanisms. I also work on neural operators, generative models, and their applications in domains such as hardware design (HDL) and weather forecasting.

Feel free to reach out!

Email  /  LinkedIn  /  Google Scholar  /  Github

profile photo

Photo taken by my love Jixuan.

News

2026.03: 🎉 Thrilled that our paper is accepted at CVPR 2026!
2026.02: 🎉 Three papers are accepted at ICASSP 2026 as Oral presentations. Looking forward to presenting in Barcelona, May 4–8, 2026!
2026.02: 🎉 Paper accepted at MLSys 2026!

Selected Publications

(*: Equal Contributions)
Multi-Scale Conditional Generative Model for Image Restoration
Shixuan Li*, Luzhe Huang*, Xiongye Xiao*, et al.
ICASSP 2026 Oral  |  Paper
SAED-Net: A Physics-Aligned Spectral Transformer for Efficient Weather Forecasting
Shixuan Li*, Wei Yang*, Peiyu Zhang, Xiongye Xiao, et al.
arXiv preprint  |  Paper
Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
Wei Yang*, Shixuan Li*, et al.
arXiv preprint  |  Paper
Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
Wei Yang*, Jiacheng Pang, Shixuan Li, et al.
arXiv preprint  |  Paper
HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL
Heng Ping*, Shixuan Li*, Peiyu Zhang*, Anzhe Cheng*, et al.
IEEE LAD 2025  |  Paper
VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation
Heng Ping, Arijit Bhattacharjee, Peiyu Zhang, Shixuan Li, et al.
MLSys 2026  |  Paper
Multi-scale Generative Modeling for Fast Sampling
Xiongye Xiao*, Shixuan Li*, Luzhe Huang*, et al.
ICASSP 2026 Oral  |  Paper
EMoE: Eigenbasis-Guided Routing for Mixture-of-Experts
Anzhe Cheng, Shukai Duan, Shixuan Li, Chenzhong Yin, Mingxi Cheng, Shahin Nazarian, Paul Thompson, Paul Bogdan
ICASSP 2026 Oral  |  Paper
ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
Anzhe Cheng*, Shukai Duan*, Shixuan Li, et al.
CVPR 2026  |  Paper
Exploring Neuron Interactions and Emergence in LLMs: From the Multifractal Analysis Perspective (NeuroMFA)
Xiongye Xiao*, Chenyu Zhou, Heng Ping, Defu Cao, Yaxing Li, Yi-Zhuo Zhou, Shixuan Li, et al.
ICLR 2025  |  Paper
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
Xiongye Xiao*, Gengshuo Liu*, Gaurav Gupta, Defu Cao, Shixuan Li, et al.
ICLR 2024  |  Paper

Education
USC University of Southern California, Los Angeles, CA
Ph.D. in Computer Engineering   Aug 2023 – Present
M.S. in Computer Engineering   Aug 2023 – May 2025
HUST Huazhong University of Science and Technology, Wuhan, China
B.E. in Computer Science   Sep 2019 – Jun 2023

Technical Skills

  • Programming Languages: Python (Proficient), C/C++, Java, SQL
  • Deep Learning Frameworks: PyTorch, TensorFlow, HuggingFace
  • Large Language Models: Multi-Agent Systems, RAG, Chain-of-Thought (CoT), Mixture-of-Experts/Agents (MoE/MoA), Prompt Engineering
  • Machine Learning & AI: Generative Models (Diffusion, GANs), Multimodal Learning, Graph Neural Networks, Transformer Architectures
  • Math & Analytical: Information Theory, Topology/Network Analysis, Multi-Fractal Analysis, Optimal Control

Services

  • Reviewer: ICLR (2025, 2026), NeurIPS 2025, ICML 2026

Mentorship

  • USC SURE (Summer Undergraduate Research Experience): mentored Michael Battiest (USC).
  • USC STAR & EHA Biotechnology Program: mentored Jezabella Figueroa (Francisco Bravo Medical Magnet High School).
  • USC SHINE (Summer High School Intensive in Next-Generation Engineering): mentored Anthony Nevarez (Alliance M. Margaret Bloomfield High School).
  • UMich COMPASS Summer Internship: mentored Risley Charles Ogembo (Glendora High School).

Miscellanea

  • I enjoy football⚽️, badminton🏸, and violin🎻.
  • I am a big fan of Lionel Messi🐐!

Template courtesy: Jon Barron.