3 papers
cs.LG2026
Reassessing Muon for Matrix Factorization
Ali Parviz, Gal Mishne, Alex Cloninger
Muon has recently emerged as a strong optimizer for large-scale deep learning, where it reshapes gradient updates through approximate orthogonalization and has been reported to out…
cs.LG2026
GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models
Yiming Zhang, Sitong Liu, Ke Li +3
Diffusion models are a leading paradigm for data generation, but training-free editing typically re-runs the full denoising trajectory for every edit strength, making iterative ref…
cs.LG2025
OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation
Yiming Zhang, Sitong Liu, Alex Cloninger
We address the computational and theoretical limitations of current distributional alignment methods for source-free unsupervised domain adaptation (SFUDA) using source class-mean…