pith. sign in

Mixed continuous and categorical flow matching for 3d de novo molecule generation.ArXiv, pages arXiv–2404

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

baseline 1

citation-polarity summary

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

roles

baseline 1

polarities

baseline 1

representative citing papers

Toward Better Geometric Representations for Molecule Generative Models

cs.LG · 2026-05-08 · unverdicted · novelty 6.0

LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.

citing papers explorer

Showing 1 of 1 citing paper.

  • Toward Better Geometric Representations for Molecule Generative Models cs.LG · 2026-05-08 · unverdicted · none · ref 56

    LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.