From the 1 of 19 linked papers with an AI index.
9 papers · 1 filter
AVQ-Attention: Adaptive Vector-Quantized Attention
Winfried van den dool, Patrick Forré, Amir Habibian +2
The paper introduces Adaptive Vector-Quantized (AVQ) Attention, which dynamically allocates codebook capacity to the most important regions of the key space, preserving O(MN) compl…
Frame-based Equivariant Diffusion Models for 3D Molecular Generation
Mohan Guo, Cong Liu, Patrick Forré
Recent methods for molecular generation face a trade-off: they either enforce strict equivariance with costly architectures or relax it to gain scalability and flexibility. We prop…
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
Lukas Fluri, Leon Lang, Alessandro Abate +3
In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward fun…
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…
Towards detailed and interpretable hybrid modeling of continental-scale bird migration
Fiona Lippert, Bart Kranstauber, Patrick Forré +1
Hybrid modeling aims to augment traditional theory-driven models with machine learning components that learn unknown parameters, sub-models or correction terms from data. In this w…
Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks
Cong Liu, David Ruhe, Patrick Forré
Most current deep learning models equivariant to or either consider mostly scalar information such as distances and angles or have a very high computational complexi…