3 papers
cs.LG2026
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Yikun Bai, Binghang Lu, Yikai Liu +7
Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and flow-matching models p…
cs.LG2026
The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models
Shuchan Wang
Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While theoretical targets favor stra…
cs.LG2026
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
Shuchan Wang
We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the watermark directly into the lear…