3 papers
cs.LG2026
Semantic Editing with Coupled Stochastic Differential Equations
Jianxin Zhang, Clayton Scott
Editing the content of an image with a pretrained text-to-image model remains challenging. Existing methods often distort fine details or introduce unintended artifacts. We propose…
cs.LG2025
Flow Straight and Fast in Hilbert Space: Functional Rectified Flow
Jianxin Zhang, Clayton Scott
Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectif…
cs.LG2024
Label Noise: Ignorance Is Bliss
Yilun Zhu, Jianxin Zhang, Aditya Gangrade +1
We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptati…