Xing Han
Postdoctoral Fellow at Johns Hopkins University

I am currently a Postdoctoral Fellow at Department of Computer Science of Johns Hopkins University, working with Prof. Suchi Saria. I graduated with Ph.D. at University of Texas at Austin, where I was associated with IDEAL, WNCG and IFML. I was advised by Prof. Joydeep Ghosh. I’ve also worked with Profs. Paul Liang, Nhat Ho and Qiang Liu on interesting research problems. I got my Bachelor’s degree in electronics and electrical engineering from The University of Edinburgh. I build multimodal foundation models and agents that acquire the core competencies of human experts: integrating heterogeneous evidence as it unfolds over time, reasoning about “what-if” trajectories, and staying reliable as the situation evolves. My work bridges core machine learning methodology with high-stakes applications such as medicine:

  • Multimodal foundation models: multimodal fusion, cross-modal interactions, clinical foundation models.
  • Counterfactual reasoning & simulation: counterfactual simulation, physiology-constrained generative models.
  • Trustworthy & enduring deployment: uncertainty quantification, sequential monitoring, continual learning.
  • Foundations of machine learning: neural scaling laws, time-series sequence models, interpretability.

I am on 2026 - 2027 academic job market, would love to connect to discuss about futures!


News
2026

Received the ICML 2026 Gold Reviewer Award.

Jun 15

Massively Multimodal Foundation Models accepted to ICLR 2026 (top ~10% of accepted papers by reviewer rating).

Jan 22
2025

Gave an invited talk on guiding Mixture-of-Experts in multimodal learning at EcoSta 2025.

Sep 15

WATCH: Adaptive Monitoring for AI Deployments accepted to ICML 2025.

May 01

Between Linear and Sinusoidal accepted to TMLR.

Apr 01
2024

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion accepted to NeurIPS 2024.

Sep 25

Novel Node Category Detection Under Subpopulation Shift accepted to ECML-PKDD 2024.

Jun 01
2023

One paper accepted to NeurIPS 2023.

Sep 22

Started my appointment as a Postdoctoral Fellow in Johns Hopkins.

Sep 01

Finished my PhD journey at UT!

Jul 17

I will start working with Prof. Suchi Saria as a Postdoctoral Fellow!

May 23
2022

Started my internship at Google.

May 31

One paper accepted to ICML 2022.

May 15

Successfully passed my qualifying exam, and now become a Ph.D. candidate!

Feb 01
2021

One paper accepted to AISTATS 2021.

Jan 22
2020

One paper accepted to NeurIPS 2020 as a spotlight presentation.

Sep 25
Selected Publications (view all )
On the Invariance and Generality of Neural Scaling Laws

Xing Han, Ziyin Liu, Suchi Saria, Paul Pu Liang

Preprint Top ~3% of NeurIPS submissions by reviewer rating

On the Invariance and Generality of Neural Scaling Laws

Xing Han, Ziyin Liu, Suchi Saria, Paul Pu Liang

Preprint Top ~3% of NeurIPS submissions by reviewer rating

FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning

Xing Han, Shravan Chaudhari, Tanvi Ranade, Rama Chellappa, Suchi Saria

Preprint

FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning

Xing Han, Shravan Chaudhari, Tanvi Ranade, Rama Chellappa, Suchi Saria

Preprint

Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-Experts

Xing Han, Hsing-Huan Chung, Joydeep Ghosh, Paul Pu Liang, Suchi Saria

International Conference on Learning Representations (ICLR) 2026 Top ~10% of accepted papers by reviewer rating

Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-Experts

Xing Han, Hsing-Huan Chung, Joydeep Ghosh, Paul Pu Liang, Suchi Saria

International Conference on Learning Representations (ICLR) 2026 Top ~10% of accepted papers by reviewer rating

QoQ-Med3: Robust Multimodal Clinical Analysis Foundation Model with Reasoning

David Dai, Jeannie She, Jiaee Cheong, Xing Han, Carl Harris, Haowen Wei, Farzan Vahedifard, Suchi Saria, Robert Stevens, Paul Pu Liang

npj Digital Medicine

QoQ-Med3: Robust Multimodal Clinical Analysis Foundation Model with Reasoning

David Dai, Jeannie She, Jiaee Cheong, Xing Han, Carl Harris, Haowen Wei, Farzan Vahedifard, Suchi Saria, Robert Stevens, Paul Pu Liang

npj Digital Medicine

WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales

Drew Prinster#, Xing Han#, Anqi Liu, Suchi Saria (# corresponding author)

International Conference on Machine Learning (ICML) 2025

WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales

Drew Prinster#, Xing Han#, Anqi Liu, Suchi Saria (# corresponding author)

International Conference on Machine Learning (ICML) 2025

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion

Xing Han, Huy Nguyen, Carl Harris, Nhat Ho, Suchi Saria

Neural Information Processing Systems (NeurIPS) 2024 Over 150 citations as of July 2026

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion

Xing Han, Huy Nguyen, Carl Harris, Nhat Ho, Suchi Saria

Neural Information Processing Systems (NeurIPS) 2024 Over 150 citations as of July 2026

Designing Robust Transformers using Robust Kernel Density Estimation

Xing Han, Tongzheng Ren, Tan Minh Nguyen, Khai Nguyen, Joydeep Ghosh, Nhat Ho

37th Conference on Neural Information Processing Systems (NeurIPS 2023)

Designing Robust Transformers using Robust Kernel Density Estimation

Xing Han, Tongzheng Ren, Tan Minh Nguyen, Khai Nguyen, Joydeep Ghosh, Nhat Ho

37th Conference on Neural Information Processing Systems (NeurIPS 2023)

Architecture Agnostic Federated Learning for Neural Networks
Architecture Agnostic Federated Learning for Neural Networks

Disha Makhija, Xing Han, Nhat Ho, Joydeep Ghosh

Proceedings of the 39th International Conference on Machine Learning (ICML) 2022

Architecture Agnostic Federated Learning for Neural Networks

Disha Makhija, Xing Han, Nhat Ho, Joydeep Ghosh

Proceedings of the 39th International Conference on Machine Learning (ICML) 2022

Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series

Xing Han, Sambarta Dasgupta, Joydeep Ghosh

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021

Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series

Xing Han, Sambarta Dasgupta, Joydeep Ghosh

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021

Certified Monotonic Neural Networks
Certified Monotonic Neural Networks

Xingchao Liu, Xing Han, Na Zhang, Qiang Liu

34th Conference on Neural Information Processing Systems (NeurIPS 2020) Spotlight presentation (280/9454 ~ 2.96%); over 185 citations as of July 2026

Certified Monotonic Neural Networks

Xingchao Liu, Xing Han, Na Zhang, Qiang Liu

34th Conference on Neural Information Processing Systems (NeurIPS 2020) Spotlight presentation (280/9454 ~ 2.96%); over 185 citations as of July 2026

All publications
Education
  • University of Texas at Austin
    University of Texas at Austin
    M.Sc. - Ph.D. in Electrical and Computer Engineering
    Aug. 2023
  • The University of Edinburgh
    The University of Edinburgh
    B.S. in Electronics and Electrical Engineering
    July 2017
Experience
  • Johns Hopkins University
    Johns Hopkins University
    Department of Computer Science
    Postdoctoral Fellow
    Sep. 2023 - present
  • Google Cloud AI
    Google Cloud AI
    Research Intern
    May 2022 - Sep. 2022
  • Intuit AI
    Intuit AI
    Research Intern
    Jun. 2021 - Sep. 2021
  • Salesforce
    Salesforce
    R&D Intern
    Jun. 2020 - Aug. 2020
  • CognitiveScale
    CognitiveScale
    Applied Scientist Intern
    May 2018 - Aug. 2018