16 papers
Distillation of Foundation Models for Time-dependent PDEs
Daniel Musekamp, Boshra Ariguib, Andrei Manolache +1
Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new do…
ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation
Loay Mualem, Vinh Tong, Samir Darouich +1
Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs. Unlike recognit…
SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model
Jan Hagnberger, Mathias Niepert
Machine learning-based surrogate models have emerged as more efficient alternatives to numerical solvers for physical simulations over complex geometries, such as car bodies. Many…
Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
Boshra Ariguib, Mathias Niepert, Andrei Manolache
High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on mo…
GraphBench: Next-generation graph learning benchmarking
Timo Stoll, Chendi Qian, Ben Finkelshtein +16
Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often r…
SymDrift: One-Shot Generative Modeling under Symmetries
Samir Darouich, Vinh Tong, LluÃs Pastor-Pérez +3
Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rotations in three-dimensional space…