Wenyuan Zhao

About Me

I am a Ph.D. student in the Department of Electrical and Computer Engineering at Texas A&M University, advised by Prof. Chao Tian.

Previously, I received my M.S. in Communication Theory & Systems at University of California San Diego, where I worked on Dynamic mmWave Networking with Prof. Xinyu Zhang. Before that, I obtained my B.E. in Information Engineering at Southeast University in 2021.

My research lies in the general area of machine learning and information theory, with a special focus on building trustworthy AI systems that can effectively handle uncertainty and leverage multimodal data.

Research Interests

Machine Learning: generative models, multimodal learning, 3D geometry models
Uncertainty Quantification: Gaussian process, Bayesian learning, evidential learning
Information Theory: information bottleneck, partial information decomposition

News

[Apr. 2026] Three papers (GPan-LoRA, SIKA-GP, Trust3R) are accepted to ICML 2026.
[Nov. 2025] ECE Poster Event Winner at Texas A&M University! (two years in a row)
[Oct. 2025] NeurIPS 2025 Scholar Award!
[Sep. 2025] Our paper about Partial Information Decomposition is accepted to NeurIPS 2025.
[Jun. 2025] Our paper about Weakly PIR is accepted to IEEE Transactions on Information Theory.
[Apr. 2025] ISIT 2025 Travel Grant Award!
[Mar. 2025] Our paper about Deep Kernel Learning is accepted to AISTATS 2025.

[Aug. 2023] Pursuing Ph.D. degree at Texas A&M University with Prof. Chao Tian!
[Nov. 2019] First-prize (top 0.7%) winner at 2019 Mathematical Contest in Modeling!

Publications

A full list of publications is available on Google Scholar.

ICML

SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning

Wenyuan Zhao, Rui Tuo, Chao Tian

The Forty-third International Conference on Machine Learning (ICML), 2026.

Early Accept

ICML

GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models

Weifeng Zhang*, Wenyuan Zhao*, Amir Hossein Rahmati, Yucheng Wang, Zhiyuan Wang, Chao Tian, Xiaoning Qian
(* Equal contribution)

The Forty-third International Conference on Machine Learning (ICML), 2026.

Early Accept

ICML

Trust3R: Unifying Feed-Forward Pointmap Prediction and Evidential Learning for Trust-Aware 3D Reconstruction

Zihao Zhu*, Wenyuan Zhao*, Nuo Chen, Chao Tian, Zhiwen Fan
(* Equal contribution)

The Forty-third International Conference on Machine Learning (ICML), 2026.

Early Accept

NeurIPS

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

Wenyuan Zhao, Adithya Balachandran, Chao Tian, Paul Pu Liang

The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.

PDF Code BibTex

AISTATS

From Deep Additive Kernel Learning to Last-layer Bayesian Neural Networks via Induced Prior Approximation

Wenyuan Zhao*, Haoyuan Chen*, Tie Liu, Tuo Rui, Chao Tian
(* Equal contribution)

The 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.

PDF Code BibTex

ISIT

Optimizing Leaky Private Information Retrieval Codes to Achieve O(log K) Leakage Ratio Exponent

Wenyuan Zhao*, Yu-Shin Huang, Chao Tian, Alex Sprintson

IEEE International Symposium on Information Theory (ISIT), 2025.

PDF BibTex

IEEE

Weakly Private Information Retrieval from Heterogeneously Trusted Servers

Wenyuan Zhao*, Yu-Shin Huang, Ruida Zhou, Chao Tian

IEEE Transactions on Information Theory.

PDF BibTex

About Me

Research Interests

News

Publications

Services

Conference Reviewers

Journal Reviewers