Xiongye Xiao

Assistant Professor

Electrical Engineering and Computer Science
University of Tennessee, Knoxville

NSF STC COMPASS (UTK PI) Foundational AI cluster AI Tennessee

AI and complex systems

I study how structure and dynamics across scales shape function in physical and AI systems. I develop mathematical and AI methods to turn this understanding into prediction and design.

I am the UTK Principal Investigator for COMPASS (Center for Complex Particle Systems), an NSF Science and Technology Center.

I joined UTK in Fall 2025 and lead the DUAL research group. I studied at the University of Southern California (Ph.D., 2019–2025) and Zhejiang University (bachelor's, 2015–2019).

Email Scholar Research

Research at DUAL

Our group

Forward ModelingandInverse Design:Quantifying structure, modeling dynamics, and guiding design across scales.AI for ScienceandScience for AI:Understanding the world with AI, and understanding AI itself.

GeoWind2Plan demo3D urban wind prediction and energy-efficient UAV planning in your browser.

RSI4ScienceDatasets & benchmarks for recursive self-improvement in scientific discovery.

Selected publications

All publications

GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning

Shaoxiang Qin, Yucheng Zhao, ..., Xiongye Xiao

NeurIPS 2026 Spotlight

GeoWind2Plan connects local, time-averaged 3D wind prediction to UAV path and speed planning, with modeled mission energy evaluated under high-fidelity CFD wind.

GeoWind2Plan framework: building geometry and background wind feed a localized neural operator, followed by wind-aware UAV path and speed optimization

Paper Try demo

Scale-Split Neural Operator for Memory- and Data-Efficient 3D Turbulence Prediction

Shaoxiang Qin, Yucheng Zhao, Zongyi Li, Liangzhu Leon Wang, and Xiongye Xiao

arXiv 2026

ScaleSplit-NO conditions local, full-resolution patch operators on a global coarse forecast for memory- and data-efficient 3D turbulence prediction.

ScaleSplit-NO architecture: a separately trained coarse Parent forecast conditions a pretrained Child operator that predicts full-resolution local patches

Preprint

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

Xiongye Xiao, Heng Ping, ..., Paul Bogdan

ICLR 2025

NeuroMFA characterizes the multifractal organization of AI weight networks across training checkpoints.

NeuroMFA representation: from a neural network to a weighted neuron interaction network

Paper Code

MIHC: Multi-view Interpretable Hypergraph Neural Networks with Information Bottleneck for Chip Congestion Prediction

Zeyue Zhang, Heng Ping, ..., Xiongye Xiao

NeurIPS 2025

MIHC combines multi-view hypergraphs and an information bottleneck for interpretable congestion prediction.

Complete MIHC framework: circuit netlists and layouts, bottleneck subgraphs, multi-view hypergraph learning and congestion prediction

Paper

Spiking dynamics of individual neurons reflect changes in the structure and function of neuronal networks

Ruochen Yang, Heng Ping, Xiongye Xiao, Roozbeh Kiani, and Paul Bogdan

Nature Communications 2025

Multifractal spiking statistics connect neuronal dynamics to network structure and function.

Co-corresponding authors: Xiongye Xiao, Roozbeh Kiani, and Paul Bogdan.

Original Figure 1 connecting network topology with neuronal spike-train dynamics

Paper

Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning

Xiongye Xiao, Gengshuo Liu, ..., Paul Bogdan

ICLR 2024

ITHP combines a neuro-inspired processing hierarchy with information bottlenecks for multimodal learning.

ITHP: primary modality X0 passes through two encoders to a predictor; detectors for X1 and X2 guide training through information constraints

Paper Code

Coupled Multiwavelet Operator Learning for Coupled Differential Equations

Xiongye Xiao, Defu Cao, ..., Paul Bogdan

ICLR 2023

CMWNO learns coupled solution operators through interacting kernels in multiwavelet space.

Coupled multiwavelet neural operator decomposition and reconstruction architecture

Paper Code

Multiwavelet-based Operator Learning for Differential Equations

Gaurav Gupta, Xiongye Xiao, and Paul Bogdan

NeurIPS 2021 Spotlight

MWT learns PDE solution operators by representing kernels in multiwavelet bases across scales.

Multiwavelet operator architecture with learned decomposition and reconstruction at successive scales

Paper

Teaching & mentorship

I teach Artificial Intelligence (COSC 423/523) and Introduction to Machine Learning (COSC 325) at UTK.

I encourage students to turn broad interests into precise questions and testable hypotheses.

Recognition & service

2026
New Faculty Highlights IEEE International Conference on Big Data
2025
Order of Areté USC's highest graduate honor at commencement
2023
Best Poster Award (1st Prize) Fall Fourier Talks, University of Maryland

ICLR / ICML (Area Chair, 2027); AAAI (Senior Program Committee, 2027).