Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S.U.N. metric for crystal generation.
Less is More: on the Over-Globalizing Problem in Graph Transformers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
A controllable synthetic benchmark on contextual SBM graphs reveals distance-misaligned training in Graph Transformers, with an oracle adaptive controller improving performance by matching task-specific distance targets.
VQ-VAE concept learning enables controllable recombination of crystal motifs to generate structures with reported gains in validity-stability-uniqueness-novelty metrics on MP-20 and Alex-MP-20.
citing papers explorer
-
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S.U.N. metric for crystal generation.
-
Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control
A controllable synthetic benchmark on contextual SBM graphs reveals distance-misaligned training in Graph Transformers, with an oracle adaptive controller improving performance by matching task-specific distance targets.
-
Composable Crystals: Controllable Materials Discovery via Concept Learning
VQ-VAE concept learning enables controllable recombination of crystal motifs to generate structures with reported gains in validity-stability-uniqueness-novelty metrics on MP-20 and Alex-MP-20.