activity
20242026
collaborators

6 papers

stat.ML2026

Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems

Yaozhong Shi, Zachary E. Ross, Yisong Yue

Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow Annealing Posterior Sampling (FA…

physics.geo-ph2026

Enforcing Reciprocity in Operator Learning for Seismic Wave Propagation

Caifeng Zou, Yaozhong Shi, Zachary E. Ross +2

Accurate and efficient wavefield modeling underpins seismic structure and source studies. Traditional methods comply with physical laws but are computationally intensive. Data-driv…

cs.LG2026

Large-Scale 3D Ground-Motion Synthesis with Physics-Inspired Latent Operator Flow Matching

Yaozhong Shi, Grigorios Lavrentiadis, Konstantinos Tsalouchidis +5

Earthquake hazard analysis and design of spatially distributed infrastructure, such as power grids and energy pipeline networks, require scenario-specific ground-motion time histor…

cs.LG2025

Mesh-Informed Neural Operator : A Transformer Generative Approach

Yaozhong Shi, Zachary E. Ross, Domniki Asimaki +1

Generative models in function spaces, situated at the intersection of generative modeling and operator learning, are attracting increasing attention due to their immense potential…

cs.LG2025

Stochastic Process Learning via Operator Flow Matching

Yaozhong Shi, Zachary E. Ross, Domniki Asimaki +1

Expanding on neural operators, we propose a novel framework for stochastic process learning across arbitrary domains. In particular, we develop operator flow matching (OFM) for lea…

cs.LG2024

Universal Functional Regression with Neural Operator Flows

Yaozhong Shi, Angela F. Gao, Zachary E. Ross +1

Regression on function spaces is typically limited to models with Gaussian process priors. We introduce the notion of universal functional regression, in which we aim to learn a pr…