7 papers
RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways
Alejandro García-Castellanos, Maurice Weiler, Erik J Bekkers
Rotary Position Embeddings (RoPE) make attention scores position-relative but leave the value pathway position-blind: the message sent by a value token is the same regardless of it…
Uncertainty-aware Machine Learning Interatomic Potentials via Learned Functional Perturbations
Olga Zaghen, Maksim Zhdanov, Dario Coscia +2
Machine Learning Interatomic Potentials (MLIPs) achieve near ab initio accuracy at a fraction of the cost of quantum-mechanical simulations, yet they remain prone to silent failure…
Flowing with Confidence
Friso de Kruiff, Dario Coscia, Max Welling +1
Generative models can produce nonsensical text, unrealistic images, and unstable materials faster than simulation or human review can absorb; without per-sample confidence, trust e…
Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
Alejandro García-Castellanos, Gijs Bellaard, Remco Duits +2
Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying different group actions, where standard techniques d…
Graph Homomorphism Distortion: A structural (pseudo)-metric for attributed graphs
Martin Carrasco, Olga Zaghen, Kavir Sumaraj +2
A large driver of the complexity of graph learning is the interplay between structure and features. When analyzing the expressivity of graph neural networks, however, existing appr…
AdS-GNN -- a Conformally Equivariant Graph Neural Network
Maksim Zhdanov, Nabil Iqbal, Erik Bekkers +1
Conformal symmetries, i.e.\ coordinate transformations that preserve angles, play a key role in many fields, including physics, mathematics, computer vision and (geometric) machine…
Pullback Flow Matching on Data Manifolds
Friso de Kruiff, Erik Bekkers, Ozan Öktem +2
We propose Pullback Flow Matching (PFM), a novel framework for generative modeling on data manifolds. Unlike existing methods that assume or learn restrictive closed-form manifold…