He Zhao

ML/AI Researcher

Hello! This is my research page.

I'm a Principal Research Scientist in machine learning and AI at CSIRO.

I'm interested in causality, uncertainty, and robustness in machine learning and AI, as well as foundation models and LLMs in science domains. For details, check out my papers and their topics below.

I'm an adjunct Senior Research Fellow at Monash University.

I regularly serve as an area chair for NeurIPS, ICML, and ICLR, and I'm on the editorial board of Machine Learning Journal. I became an IEEE Senior Member in 2026.

My first name is He, a common Chinese name with an interesting spelling in English. Its pronunciation is roughly similar to the English word “her,” but without the “r” sound.

My KDD 2023 paper won the Best Student Paper Award.
The Asian Conference on Machine Learning (ACML 2026, 1–4 Dec) will be held in Melbourne, right before NeurIPS in Sydney.

Research output

Selected publications

53 papers shown

TopicSort

Year	Publication
2026	NeurIPS Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task L. He, J. Guo, Y. Wang, Y. Yang, H. Zhao, S. Wan, D. Wang, L. Yao, T. Liu LLMs
2026	EMNLP Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration Z. Wang, B. Zhang, H. Zhao, D. Guo LLMsUncertainty, Robustness, Safety
2026	NeurIPS ATTRIB Workshop From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models H. Zhao, R. Thompson, D. M. Steinberg, A. Rahman, E. V. Bonilla, C. S. Ong arxiv Tabular Data
2026	KDD Ordering-based Causal Discovery via Generalized Score Matching V. Vo, T. Le, H. Zhao, E. V. Bonilla, D. Phung arxiv Causality
2026	Preprint A Comprehensive Survey of Tabular Anomaly Detection H. Ye, J. Liu, Y. Yao, J. Li, P. Wang, Y. Cao, H. Zhao, D. Guo, Y. Chang, H. Zha Tabular Data
2026	ACL Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment H. Wang, Z. Li, Y. Yang, H. Zhao, H. Zha, D. Guo arxiv LLMsUncertainty, Robustness, Safety
2026	CVPR FindingsCVPR Compute Transparency Champion FedNPC: Stochastic Noise-driven Post-hoc Classifier Calibration Method for Federated Long-tailed Learning J. Gao, H. Zhao, Y. Yang, D. Guo award code Federated Learning
2026	Preprint Arrow: A Foundation Model for Causal Discovery R. Thompson, H. Zhao, D. M. Steinberg, E. V. Bonilla arxiv code CausalityTabular Data
2026	NeurIPSSpotlight, Top 3% LLM Meeting Decision Trees on Tabular Data H. Ye, J. Li, H. Zhao, D. Guo, Y. Chang code LLMsTabular Data
2026	ICLR Imitating the Truth: Attention-aware Truth-Guided Enhancement for Hallucination Mitigation in Large Vision-Language Models H. Ren, Z. Wang, Y. Yang, H. Zhao, F. Tang, D. Guo, Y. Chang LLMsVision
2026	ICLR LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis H. Ye, J. Li, H. Zhao, M. Zhuge, D. Guo, Y. Chang, H. Zha LLMsTabular Data
2026	ICLR Unifying Stable Optimization and Reference Regularization in RLHF L. He, Q. Qu, H. Zhao, S. Wan, D. Wang, L. Yao, T. Liu LLMs
2026	IJCV Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score M.C. Jung, J. Dipnall, B. Gabbe, H. Zhao code VisionUncertainty, Robustness, Safety
2026	TPAMI Deep Tabular Representation Corrector H. Ye, P. Wang, W. Fan, X. Song, H. Zhao, D. Guo, Y. Chang Tabular Data
2026	ICML Causal Preference Elicitation E. V. Bonilla, H. Zhao, D. M. Steinberg arxiv code CausalityBayesian Models
2026	ICML Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems X. Wang, M. Groom, R. Oliveira, H. Zhao, T. O'Kane, E. V. Bonilla arxiv AI for Science
2026	TMLR HiBaNG: Hierarchical Bayesian Nonparametric Granger Causal Discovery in Low-Data Regimes H. Zhao, V. Kitsios, T. O'Kane, E. V. Bonilla CausalityAI for ScienceBayesian Models
2025	ICMLOral, Top 1% Rényi Neural Processes X. Wang, H. Zhao, E. V. Bonilla code Uncertainty, Robustness, SafetyBayesian Models
2025	ACLMain Conference Neural Topic Modeling with Large Language Models in the Loop X. Yang, H. Zhao, W. Xu, Y. Qi, J. Lu, D. Phung, L. Du code LLMsText Understanding
2025	CVPR Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration J. Ni, H. Zhao, J. Gao, D. Guo, H. Zha VisionUncertainty, Robustness, Safety
2025	CVPR Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning H. Ren, F. Tang, H. Zhao, Z. Wang, D. Guo, Y. Chang VisionLLMs
2025	CVPR FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors C. Shi, H. Zhao, B. Zhang, M. Zhou, D. Guo, Y. Chang code Federated LearningVision
2025	ICLR DRL: Decomposed Representation Learning for Tabular Anomaly Detection H. Ye, H. Zhao, W. Fan, M. Zhou, D. Guo, Y. Chang Tabular Data
2025	ICLR FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking C. Shi, J. Li, H. Zhao, D. Guo, Y. Chang Federated Learning
2025	TACLPresented at ACL 2025 LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models X. Yang, H. Zhao, D. Phung, W. Buntine, L. Du code LLMsText Understanding
2024	ICML Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification J. Gao, H. Zhao, D. Guo, H. Zha code VisionOptimal Transport
2024	ICML Parameter Estimation in DAGs from Incomplete Data via Optimal Transport V. Vo, T. Le, L. T. Vuong, H. Zhao, E. V. Bonilla, D. Phung code CausalityOptimal Transport
2024	ICLRSpotlight, Top 5% PTaRL: Prototype-based Tabular Representation Learning via Space Calibration H. Ye, W. Fan, X. Song, S. Zheng, H. Zhao, D. Guo, Y. Chang code Tabular Data
2023	NeurIPS Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation M.C. Jung, H. Zhao, J. Dipnall, L. Du code Uncertainty, Robustness, Safety
2023	NeurIPS Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification J. Gao, H. Zhao, Z. Li, D. Guo code Optimal TransportVision
2023	NeurIPS NPCL: Neural Processes for Uncertainty-Aware Continual Learning S. Jha, D. Gong, H. Zhao, L. Yao code Uncertainty, Robustness, Safety
2023	KDDBest Student Paper Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations V. Vo, T. Le, V. Nguyen, H. Zhao, E. V. Bonilla, G. Haffari, D. Phung award code Causality
2023	ICML Transformed Distribution Matching for Missing Value Imputation H. Zhao, K. Sun, A. Dezfouli, E. V. Bonilla code Optimal TransportTabular Data
2023	ICML Vector Quantized Wasserstein Auto-Encoder L.T. Vuong, T. Le, H. Zhao, C. Zheng, M. Harandi, J. Cai, D. Phung code Optimal TransportVision
2023	TMLR Generating Adversarial Examples with Task Oriented Multi-Objective Optimization A. Bui, T. Le, H. Zhao, Q. Tran, P. Montague, D. Phung code Uncertainty, Robustness, Safety
2022	NeurIPS Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport D. Guo, L. Tian, H. Zhao, M. Zhou, H. Zha code Optimal TransportVision
2022	NeurIPS Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification D. Guo, Z. Li, M. Zheng, H. Zhao, M. Zhou, H. Zha code Optimal TransportVision
2022	NeurIPS Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture M.C. Jung, H. Zhao, J. Dipnall, B. Gabbe, L. Du code Uncertainty, Robustness, Safety
2022	AISTATS On Global-view Based Defense via Adversarial Attack and Defense Risk Guaranteed Bounds T. Le, A. Bui, M.T.T. Le, H. Zhao, P. Montague, Q. Tran, D. Phung Uncertainty, Robustness, Safety
2022	AISTATS Particle-based Adversarial Local Distribution Regularization T. Nguyen-Duc, T. Le, H. Zhao, J. Cai, D. Phung Uncertainty, Robustness, Safety
2022	ICLR Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings D. Wang, D. Guo, H. Zhao, H. Zheng, K. Tanwisuth, B. Chen, M. Zhou code Optimal TransportText Understanding
2022	ICLR A Unified Wasserstein Distributional Robustness Framework for Adversarial Training A. Bui, T. Le, Q. Tran, H. Zhao, D. Phung code Optimal TransportUncertainty, Robustness, Safety
2021	IJCAISurvey Track Topic Modelling Meets Deep Neural Networks: A Survey H. Zhao, D. Phung, V. Huynh, Y. Jin, L. Du, W. Buntine arxiv Text Understanding
2021	ICLRSpotlight, Top 5% Neural Topic Model via Optimal Transport H. Zhao, D. Phung, V. Huynh, T. Le, W. Buntine code Text UnderstandingOptimal Transport
2020	ECCV Improving Adversarial Robustness by Enforcing Local and Global Compactness A. Bui, T. Le, H. Zhao, P. Montague, O. de Vel, T. Abraham, D. Phung arxiv code Uncertainty, Robustness, Safety
2020	AISTATS Variational Autoencoders for Sparse and Overdispersed Discrete Data H. Zhao, P. Rai, L. Du, W. Buntine, D. Phung, M. Zhou code Text UnderstandingBayesian Models
2020	NeurIPS OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling V. Huynh, H. Zhao, D. Phung Text UnderstandingOptimal Transport
2018	ICML Inter and Intra Topic Structure Learning with Word Embeddings H. Zhao, L. Du, W. Buntine, M. Zhou code Text UnderstandingBayesian Models
2018	AISTATS Bayesian Multi-label Learning with Sparse Features and Labels, and Label Co-occurrences H. Zhao, P. Rai, L. Du, W. Buntine code Tabular DataBayesian Models
2018	NeurIPS Dirichlet Belief Networks for Topic Structure Learning H. Zhao, L. Du, W. Buntine, M. Zhou code Text UnderstandingBayesian Models
2017	ACML A Word Embeddings Informed Focused Topic Model H. Zhao, L. Du, W. Buntine code Text UnderstandingBayesian Models
2017	ICDMLong Paper MetaLDA: A Topic Model that Efficiently Incorporates Meta Information H. Zhao, L. Du, W. Buntine, G. Liu arxiv code Text UnderstandingBayesian Models
2017	ICML Leveraging Node Attributes for Incomplete Relational Data H. Zhao, L. Du, W. Buntine arxiv code Tabular DataBayesian Models

Community

Professional services

Reviewing

NeurIPS Area Chair (2025-); top reviewer in 2018, top area chair in 2026
ICLR Area Chair (2025-)
ICML Area Chair (2026-)
Machine Learning Journal editorial board member (2023-)

Organising

Tutorial Chair Asian Conference on Machine Learning, 2026
OT-SDMG: Workshop on Optimal Transport for Structured Data Modeling and Generation The Web Conference, 2025
Tutorial: Optimal Transport for Unsupervised Learning Asian Conference on Machine Learning, 2021

Speaking

Recent talks

Aligning Probabilistic Distributions via Optimal Transport for Machine Learning Problems

Melbourne Trustworthy Machine Learning and Reasoning Seminars , 2025

link

From Data to Representations: Distribution Alignment in Machine Learning via Optimal Transport

Workshop on Modern Statistical Perspectives on Machine Learning, The University of Melbourne , 2025

LLMs as “Prior” for Local Data Analysis

Monash NLP Group , 2025

Beyond Predictions: Making AI Reliable with Uncertainty and Causal Understanding

UNSW AI Symposium , 2024

link

Enhancing Generalisation and Robustness in Deep Learning with Optimal Transport

School of Computer Science and Engineering, UNSW , 2024

Learning Deep Representations with Optimal Transport

Statistics Seminar, The University of Sydney , 2024

link

He Zhao

Selected publications

From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models

Ordering-based Causal Discovery via Generalized Score Matching

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment

Arrow: A Foundation Model for Causal Discovery

Causal Preference Elicitation

Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems

Professional services

Reviewing

Organising

Recent talks

Aligning Probabilistic Distributions via Optimal Transport for Machine Learning Problems

From Data to Representations: Distribution Alignment in Machine Learning via Optimal Transport

LLMs as “Prior” for Local Data Analysis

Beyond Predictions: Making AI Reliable with Uncertainty and Causal Understanding

Enhancing Generalisation and Robustness in Deep Learning with Optimal Transport

Learning Deep Representations with Optimal Transport