Jiachen Yao

About Me

Hello! This is Jiachen. ▶ More about my name… Jiachen is pronounced “chia-ch’en”. Feel free to call me James!

I’m a Ph.D. student in Computing and Mathematical Sciences at Caltech, where I am fortunate to be advised by Professor Anima Anandkumar. My research lies at the intersection of generative modeling and scientific computing.

Prior to Caltech, I completed my undergraduate studies at Tsinghua University, where I had the privilege of working with Professor Jun Zhu and Professor Hang Su on physics-informed machine learning. I am also grateful for the opportunity to pursue research at Stanford University, where I worked with Professor James Landay and Professor Monica Lam on human-AI interaction.

Research Interests

My long term goal is to develop a unified framework that learns and uses efficient representations of data, domain knowledge, and available observations to model complex systems. I am particularly interested in generative approaches to achieve this objective.

I work in the intersection of generative modeling and physical sciences. Scientific (inverse) problems are often ill-posed and non-unique, which motivates probabilistic sampling approaches. The strong priors offered by generative models can significantly enhance robustness and efficiency, while physics laws and principles, if incorporated properly, can further improve the quality and stability of generated solutions. Therefore, I am developing scalable, uncertainty-aware methods for generative models + scientific inverse problems.

News

• [Nov. 2026] I’ll give an invited talk on consistency learning for chaotic dynamics at the 2nd Workshop on Learning Dynamical System (WLDS2), hosted by RIKEN AIP in Japan, on November 26th!
• [Oct. 2026] Our paper, “PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers,” has been accepted to NeurIPS 2026 Evaluations & Datasets Track. See you in Atlanta!
• [Oct. 2026] Our paper, “GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning,” has been accepted to NeurIPS 2026 as a Spotlight.
• [Jun. 2026] I’ll begin my research internship at Amazon Web Services (AWS) in Sunnyvale, working on sampling for time series. Happy to catch up!

Publications

Services

As a reviewer

• NeurIPS 2024-2025, ICML 2025, ICLR 2025
• Journal of Machine Learning Research (JMLR)
• Transactions on Machine Learning Research (TMLR)
• Nature Communications

Invited talks

• 2nd Workshop on Learning Dynamical System (WLDS2), RIKEN AIP, 2026.
• Keynote for ICLR 2026 Workshop on AI & PDE, Brazil, 2026.
• SIAM Conference on Uncertainty Quantification, Minneapolis, 2026.
• AI & Scientific Discovery Workshop, UChicago, 2025.
• MURI Annual Review Meeting, Caltech, 2025.
• Academia-Industry X Workshop, Caltech, 2024.

Honors and Awards

Graduate Honors

• Naren and Vinita Gupta Sensing to Intelligence Fellowship
• Professor Anatol Roshko Fellowship

Undergrad Honors

• Outstanding Graduate by the Beijing Ministry of Education
• Outstanding Graduate by Zhili College
• National Scholarship (highest undergrad honor in China, top 0.2% nationwide)
• Selected to UGVR Program to conduct a summer research internship at Stanford (fully funded)
• Selected to Spark Program at Tsinghua University (top 1%)
• Tsinghua Scholarship for Comprehensive Excellence
• Tsinghua Scholarship for Innovation
• Zhili College Dean’s List (7/219)
• Silver Medal in National Olympiad in Informatics (top 100 nationwide)

Personal Interests

Hobbies

• Badminton, Tennis
• Blogging, Movies
• Cooking
• Coding, Cloud deployment

Technical Skills

• Python, C/C++, JavaScript/TypeScript, MATLAB
• PyTorch, Jax, Huggingface, React, Vue
• Linux, Git, Docker

Powered by Jekyll and Minimal Light theme.