April 23, 2024, 4:43 a.m. | Romain Lacombe, Neal Vaidya

cs.LG updates on arXiv.org arxiv.org

arXiv:2404.13491v1 Announce Type: cross
Abstract: Recent advances in fast sampling methods for diffusion models have demonstrated significant potential to accelerate generation on image modalities. We apply these methods to 3-dimensional molecular conformations by building on the recently introduced GeoLDM equivariant latent diffusion model (Xu et al., 2023). We evaluate trade-offs between speed gains and quality loss, as measured by molecular conformation structural stability. We introduce Equivariant Latent Progressive Distillation, a fast sampling algorithm that preserves geometric equivariance and accelerates generation …

abstract advances apply arxiv building cs.lg diffusion diffusion model diffusion models distillation image latent diffusion models q-bio.qm sampling type

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York