pith. sign in

Geometric latent diffusion models for 3d molecule generation

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.AI 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

background 2

polarities

background 2

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 2 of 2 citing papers.

  • Toward Better Geometric Representations for Molecule Generative Models cs.LG · 2026-05-08 · unverdicted · none · ref 24

    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.

  • From Single-Step Edit Response to Multi-Step Molecular Optimization cs.AI · 2026-05-11 · unverdicted · none · ref 48

    A new method decomposes property differences between weakly related molecules into minimal chemical edits to train a directional evaluator that guides multi-step optimization with less oracle querying.