ICML 2025 - 1 paper accepted
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
I have been leading AIML@K since 2020, with the goal of educating future leaders and colleagues aware of the importance of bridging artificial intelligence and mathematics.
My research area covers both theoretical and practical sides of artificial intelligence.
I believe that research with solid ties to applications with practical impact is as important as research in abstract setting with high generalizability.
Interests
- Theory of Artificial Intelligence and Machine Learning
- (Sub)optimality in Learning under Uncertainty
- Sequential Decision Making by Agents
- Making Real Impact with Technology
Education
Ph.D. in Computer Science
Princeton University
M.S. in Computational Biology
Carnegie Mellon University
B.A. in Biochemistry
Columbia University in the City of New York
Recent News
One paper accepted to AAAI 2025
ABC3 (Active Bayesian Causal Inference with Cohn Criteria)
Featured
Publications
(2025).
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition.
In ICML 2025.
(2025).
ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments.
In AAAI 2025.
(2024).
Pre-trained Language Models Return Distinguishable Probability Distributions to Unfaithfully Hallucinated Texts.
In EMNLP 2024 Findings.
(2024).
PPSD GAN: PPSD-informed Generative Model for Ambient Seismic Noise Synthesizing.
In IEEE GRSL.
(2024).
Bypassing Stationary Points in Training Deep Learning Models.
In IEEE TNNLS.
(2022).
Online Learning with Regularized Knowledge Gradients.
In PAKDD 2022.
(2019).
Bias-Corrected Q-Learning With Multistate Extension.
In IEEE TAC.