Dongxia Wu

Dongxia Wu

Assistant Professor, MBZUAI

Statistics and Data Science · Machine Learning

ATLAS Lab — AI for Trustworthy Learning And Science

Trustworthy, world-grounded AI for scientific discovery.

Dongxia [dot] Wu [at] mbzuai [dot] ac [dot] ae

I am a tenure-track Assistant Professor at MBZUAI, jointly in the Department of Statistics and Data Science and the Department of Machine Learning, where I lead the ATLAS Lab (AI for Trustworthy Learning And Science).

Previously, I was a postdoctoral scholar at Stanford University, working with Prof. Emily B. Fox. I received my Ph.D. in Computer Science from UC San Diego in 2025, advised by Prof. Rose Yu and Prof. Yi-An Ma, and my B.S. in Applied Mathematics, Physics, and Computer Science from UW–Madison in 2020.

My research builds trustworthy AI — calibrated, auditable, and physics-grounded models — and applies it to AI for science, from molecular and cellular biology to the spatiotemporal dynamics of the physical world (toward scientific world models).

News

Openings

Postdoctoral Researcher — Virtual Cell Modeling

Now hiring
MBZUAI, Abu Dhabi Flexible start date Open until filled

Co-advised by Prof. Dongxia Wu and Prof. Le Song, this postdoc will build foundation-model approaches to virtual cell modeling.

Research directions

  1. Multiscale and multimodal cell foundation models.
  2. A unified cell world model for understanding, predicting, simulating, and programming biology.
  3. Trustworthy, mechanistically grounded modeling from a systems-biology perspective — ensuring cell perturbations respect mechanistic constraints (biological correctness).

What we offer

  • Co-advising by Prof. Dongxia Wu and Prof. Le Song.
  • Ample GPU resources to train foundation models.
  • Collaboration with GenBio AI and the Stanford Institute for Human-Centered AI.
  • Competitive salary and benefits.

Responsibilities

  • Develop novel AI and ML methodologies.
  • Conduct interdisciplinary research with collaborators in academia and industry.
  • Publish at leading conferences and journals.
  • Guide junior students in their research.

Qualifications

  • Ph.D. in Computer Science, Computational Biology, AI/ML, Statistics, or a closely related field.
  • Strong AI-for-biology background, with a publication record at leading venues (ICML, NeurIPS, ICLR, CVPR, …) and journals (e.g., Nature-family).
  • Strong collaborative, verbal, and written communication skills.

To apply, email your CV, a brief research statement, and 2 references to Dongxia [dot] Wu [at] mbzuai [dot] ac [dot] ae with the subject line Postdoc — Virtual Cell Modeling.

Research

The ATLAS Lab (AI for Trustworthy Learning And Science) builds machine learning that is trustworthy — calibrated, auditable, and physics-grounded — and uses it to advance science, with a focus on biology and the spatiotemporal dynamics of the physical world. My research spans two intertwined thrusts:

Trustworthy AI

Calibrated, auditable, and physics-grounded models.

As AI moves into high-stakes scientific decisions, accuracy alone is not enough. Models must know what they don’t know (calibrated uncertainty), expose why they decided (auditability), and respect known physical and biological laws (physics-grounded inductive bias). I develop probabilistic and generative methods — Bayesian deep learning, uncertainty quantification, and constrained generative modeling — that turn black-box predictions into reliable, accountable decisions.

AI for Science

From molecular and cellular biology to the spatiotemporal dynamics of the world.

Scientific data are scarce, noisy, multi-fidelity, and structured across space and time. I build generative and Bayesian models that learn efficiently from such data to accelerate discovery — especially in biology, spanning molecule, protein, and material design, single-cell modeling, and biomedical imaging — and to build world models that capture how complex physical systems evolve across space and time, from fluid dynamics to the climate. I also take a data-centric view, curating open datasets and rigorous benchmarks that make progress in AI for science measurable and reproducible.

Group

Lab Members

Mentoring Experience

Prospective Students

The ATLAS Lab at MBZUAI is recruiting! I am looking for highly motivated PhD students, master’s students, postdocs, research assistants (RAs), and visiting students, and I recruit from both the Department of Statistics and Data Science and the Department of Machine Learning. PhD positions begin in Fall 2027; postdoc, master’s, RA, and visiting positions are open now, with flexible start dates. I am especially interested in candidates working across these areas:

If you would like to work with me, please email your CV, academic transcript, and a brief research statement to Dongxia [dot] Wu [at] mbzuai [dot] ac [dot] ae, using the subject line [Your Name] — [Position] — [Research Direction(s)] — ATLAS Lab Application. In your email, please note which of the four directions above best match your interests and why.

Publications

For a full and up-to-date list, see my Google Scholar.

Preprints
  1. Calibrating LLMs with Semantic-level Reward Fengfei Yu, Ruijia Niu, Dongxia Wu, Yi-An Ma, Rose Yu. arXiv preprint 2026
  2. BALAR: A Bayesian Agentic Loop for Active Reasoning Aymen Echarghaoui, Dongxia Wu, Emily B. Fox. arXiv preprint 2026
  3. Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging Dongxia Wu, Yuhui Zhang, Serena Yeung-Levy, Emma Lundberg, Emily B. Fox. arXiv preprint 2026
2026
  1. CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning Dongxia Wu, Shiye Su, Yuhui Zhang, Elaine Sui, Emma Lundberg, Emily B. Fox, Serena Yeung-Levy. European Conference on Computer Vision (ECCV) 2026
  2. Divide and Learn: Multi-Objective Combinatorial Optimization at Scale Esha Singh, Dongxia Wu, Chien-Yi Yang, Tajana Rosing, Rose Yu, Yi-An Ma. International Conference on Machine Learning (ICML) 2026
2025
  1. MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning Peter Eckmann, Dongxia Wu, Germano Heinzelmann, Michael K Gilson, Rose Yu. International Conference on Machine Learning (ICML) 2025
  2. Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints Lingkai Kong, Yuanqi Du, Wenhao Mu, Kirill Neklyudov, Valentin De Bortoli, Dongxia Wu, Haorui Wang, Aaron Ferber, Yi-An Ma, Carla P. Gomes, Chao Zhang. International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
2024
  1. Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes Dongxia Wu, Tsuyoshi Idé, Aurélie Lozano, Georgios Kollias, Jiří Navrátil, Naoki Abe, Yi-An Ma, Rose Yu. International Conference on Artificial Intelligence and Statistics (AISTATS) 2024
  2. Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling Ruijia Niu, Dongxia Wu, Kai Kim, Yi-An Ma, Duncan Watson-Parris, Rose Yu. International Conference on Machine Learning (ICML) 2024
  3. Diff-BBO: Diffusion-Based Inverse Modeling for Black-Box Optimization Dongxia Wu, Nikki Lijing Kuang, Ruijia Niu, Yi-An Ma, Rose Yu. NeurIPS Workshop on Bayesian Decision-making and Uncertainty 2024
  4. Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs Ruijia Niu, Dongxia Wu, Rose Yu, Yi-An Ma. NeurIPS Workshop on Statistical Foundations of LLMs and Foundation Models 2024
  5. GLEAM-AI: Neural Surrogate for Accelerated Epidemic Analytics and Forecasting Mohammadmehdi Zahedi, Dongxia Wu, Jessica T. Davis, Yi-An Ma, Alessandro Vespignani, Rose Yu, Matteo Chinazzi. NeurIPS Workshop on Bayesian Decision-making and Uncertainty 2024
2023
  1. Disentangled Multi-Fidelity Deep Bayesian Active Learning Dongxia Wu, Ruijia Niu, Matteo Chinazzi, Yi-An Ma, Rose Yu. International Conference on Machine Learning (ICML) 2023
  2. Deep Bayesian Active Learning for Accelerating Stochastic Simulation Dongxia Wu, Ruijia Niu, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2023
2022
  1. Multi-Fidelity Hierarchical Neural Processes Dongxia Wu, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2022
  2. DeepViFi: Detecting Oncoviral Infections in Cancer Genomes Using Transformers Utkrisht Rajkumar, Sara Javadzadeh, Mihir Bafna, Dongxia Wu, Rose Yu, Jingbo Shang, Vineet Bafna. ACM Conference on Bioinformatics, Computational Biology and Health Informatics (BCB) 2022
  3. Evaluation of Individual and Ensemble Probabilistic Forecasts of COVID-19 Mortality in the United States Estee Cramer, et al. (including Dongxia Wu). Proceedings of the National Academy of Sciences (PNAS) 2022
2021
  1. Quantifying Uncertainty in Deep Spatiotemporal Forecasting Dongxia Wu, Liyao Gao, Xinyue Xiong, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2021
  2. DeepGLEAM: A Hybrid Mechanistic and Deep Learning Model for COVID-19 Forecasting Dongxia Wu, Liyao Gao, Xinyue Xiong, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu. arXiv preprint 2021
  3. A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations Mingren Shen, Guanzhao Li, Dongxia Wu, et al. Computational Materials Science 2021
  4. Multi-Defect Detection and Analysis of Electron Microscopy Images with Deep Learning Mingren Shen, Guanzhao Li, Dongxia Wu, et al. Computational Materials Science 2021