9 papers
Kernel-Gradient Drifting Models
Maria Esteban-Casadevall, Jorge Carrasco-Pollo, Max Welling +3
We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting models with directions induced by…
Riemannian Variational Flow Matching for Material and Protein Design
Olga Zaghen, Floor Eijkelboom, Alison Pouplin +4
We present Riemannian Gaussian Variational Flow Matching (RG-VFM), a geometric extension of Variational Flow Matching (VFM) for generative modeling on manifolds. Motivated by the b…
Controlled Generation with Equivariant Variational Flow Matching
Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama +4
We derive a controlled generation objective within the framework of Variational Flow Matching (VFM), which casts flow matching as a variational inference problem. We demonstrate th…
On Equivariant Model Selection through the Lens of Uncertainty
Putri A. van der Linden, Alexander Timans, Dharmesh Tailor +1
Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored…
On the Importance of Embedding Norms in Self-Supervised Learning
Andrew Draganov, Sharvaree Vadgama, Sebastian Damrich +4
Self-supervised learning (SSL) allows training data representations without a supervised signal and has become an important paradigm in machine learning. Most SSL methods employ th…
Probing Equivariance and Symmetry Breaking in Convolutional Networks
Sharvaree Vadgama, Mohammad Mohaiminul Islam, Domas Buracas +3
In this work, we explore the trade-offs of explicit structural priors, particularly group equivariance. We address this through theoretical analysis and a comprehensive empirical s…