1 code implementation • 21 Apr 2024 • Romain Lacombe, Neal Vaidya
We introduce Equivariant Latent Progressive Distillation, a fast sampling algorithm that preserves geometric equivariance and accelerates generation from latent diffusion models.
1 code implementation • 4 Dec 2023 • Romain Lacombe, Lucas Hendren, Khalid El-Awady
Here we introduce AdsorbRL, a Deep Reinforcement Learning agent aiming to identify potential catalysts given a multi-objective binding energy target, trained using offline learning on the Open Catalyst 2020 and Materials Project data sets.
Multi-Objective Reinforcement Learning reinforcement-learning
1 code implementation • 28 Nov 2023 • Romain Lacombe, Kerrie Wu, Eddie Dilworth
Evaluating the accuracy of outputs generated by Large Language Models (LLMs) is especially important in the climate science and policy domain.
no code implementations • 22 Jul 2023 • Romain Lacombe, Andrew Gaut, Jeff He, David Lüdeke, Kateryna Pistunova
Deep learning in computational biochemistry has traditionally focused on molecular graphs neural representations; however, recent advances in language models highlight how much scientific knowledge is encoded in text.
no code implementations • 31 Mar 2023 • Romain Lacombe, Hannah Grossman, Lucas Hendren, David Lüdeke
To advance automated detection of extreme weather events, which are increasing in frequency and intensity with climate change, we explore modifications to a novel light-weight Context Guided convolutional neural network architecture trained for semantic segmentation of tropical cyclones and atmospheric rivers in climate data.