Hanming Yang
hy2781 [at] columbia [dot] edu ·
Google Scholar ·
GitHub ·
CV
I am a first-year PhD student in the
Decision, Risk, and Operations
division at Columbia University, where I am fortunate to work with
Prof. Hongseok Namkoong and
Prof. Jing Dong.
Before my PhD, I spent two years at Google working on
post-training. I did my undergrad at Middlebury College and Columbia.
I am interested in principled and useful ideas that draw from machine learning,
operations research, and statistics. I also go by Albert.
Research
-
Rare Event Estimation via Iterative Unalignment [pdf]
H. Yang, D. Mittal, J. Dong, H. Namkoong.
-
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini [pdf]
M. Shanbhogue, Z. Li, …, A. Yang, …, M. Seyedhosseini.
Technical Report, 2026.
-
Pre-training and In-context Learning is Bayesian Inference a la de Finetti [pdf]
N. Ye, H. Yang, A. Siah, H. Namkoong.
ICLR Workshop on Mathematical and Empirical Understanding of Foundation Models (ME-FoMo), 2024.
-
Variational Pseudo Marginal Methods for Jet Reconstruction in Particle Physics [pdf]
H. Yang*, A. K. Moretti*, S. Macaluso, P. Chlenski, C. A. Naesseth, I. Pe'er.
Transactions on Machine Learning Research (TMLR), 2024.
-Journal-to-Conference (J2C) Certification. Presented at ICLR 2026.
-
Towards End-to-End Structure Determination from X-ray Diffraction Data Using Deep Learning [pdf]
G. Guo, J. Goldfeder, L. Lan, A. Ray, A. H. Yang, B. Chen, S. J. L. Billinge, et al.
npj Computational Materials, 2024.
* Equal contribution.