ATLAS: A Foundation Neural Sampler for Amorphous Materials
Amorphous materials exhibit exceptional mechanical and functional properties, yet their rugged energy landscapes are notoriously difficult to sample. Below the glass-transition temperature, conventional molecular dynamics and Monte Carlo become inefficient because equilibration relies on rare barrier-crossing events, while data-driven generative models are constrained by scarce and biased reference ensembles. Here, we introduce ATLAS, an efficient sampler that learns a diffusion process to generate Boltzmann-distributed amorphous structures directly from a target energy function. Parameterized
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 59%Guiding generative models to uncover diverse and novel crystals via reinforcement learning →
- PossiblePossibly related (embedding) · 47%Reshaping biomolecular structure prediction through strategic conformational exploration with HelixFold-S1 →
- FuzzyOverlapping authors or contributors · 62%DietrichGebert/ponytail →
“Shared author/contributor keys: cheng”
- LinkedLinked via arxiv author · 85%Mouyang Cheng →
“ATLAS: A Foundation Neural Sampler for Amorphous Materials”
- LinkedLinked via arxiv author · 85%Denis Blessing →
“ATLAS: A Foundation Neural Sampler for Amorphous Materials”
- LinkedLinked via arxiv author · 85%Botao Yu →
“ATLAS: A Foundation Neural Sampler for Amorphous Materials”
- LinkedLinked via arxiv author · 85%Gerhard Neumann →
“ATLAS: A Foundation Neural Sampler for Amorphous Materials”
- LinkedLinked via arxiv author · 85%Mingda Li →
“ATLAS: A Foundation Neural Sampler for Amorphous Materials”