Pith. sign in

REVIEW 10 cited by

Equivariant Diffusion for Molecule Generation in 3D

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.17003 v2 pith:I2WFYYJQ submitted 2022-03-31 cs.LG q-bio.QMstat.ML

classification cs.LGq-bio.QMstat.ML
keywords diffusionequivariantmodelatomgenerationmoleculeadditionadmits
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This work introduces a diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Our E(3) Equivariant Diffusion Model (EDM) learns to denoise a diffusion process with an equivariant network that jointly operates on both continuous (atom coordinates) and categorical features (atom types). In addition, we provide a probabilistic analysis which admits likelihood computation of molecules using our model. Experimentally, the proposed method significantly outperforms previous 3D molecular generative methods regarding the quality of generated samples and efficiency at training time.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Graph Completion Method that Jointly Predicts Geometry and Topology Enables Effective Molecule Assembly

    q-bio.QM 2025-05 conditional novelty 7.0 of 10

    EdGr jointly predicts inter-fragment bonds and atomic positions via coupled diffusion, outperforming prior methods on molecule assembly.

  2. A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules

    cs.LG 2025-05 conditional novelty 7.0 of 10

    A valence-preserving double edge-swap diffusion model with a learned time estimator generates chemically valid molecules with property distributions closer to real molecules than JTVAE and DiGress on the GuacaMol benchmark.

  3. Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics

    cs.LG 2026-04 conditional novelty 6.5 of 10

    Structure-pretrained diffusion plus an equivariant temporal interpolator generates chemically realistic MD trajectories on small molecules, tetrapeptides, and proteins by separating spatial and temporal learning.

  4. Atomic Design Transformer: Scaffold-Conditioned 3D Molecule Generation via xTB-Reward Reinforcement Learning

    physics.comp-ph 2026-07 conditional novelty 6.0 of 10

    A plain causal transformer that tokenizes atom positions in local frames generates 3D molecules directly; RL against an xTB relaxation reward lifts topology-preserving valid yield from ~50% to ~95%.

  5. Differentiable Normative Guidance for Nash Bargaining Solution Recovery

    cs.GT 2026-03 conditional novelty 6.0 of 10

    Guided graph diffusion with a differentiable Nash-product penalty recovers individually rational, near-Nash-bargaining utility splits without explicit Pareto frontier knowledge.

  6. MiAD: Mirage Atom Diffusion for De Novo Crystal Generation

    cs.LG 2025-11 conditional novelty 6.0 of 10

    Mirage infusion lets crystal diffusion models vary atom counts during generation and raises the S.U.N. rate on MP-20 to 8.2%.

  7. InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames

    cs.LG 2025-10 conditional novelty 6.0 of 10

    An autoregressive transformer with inertial-frame tokenization and geometric rotary positional encoding reports state-of-the-art validity and stability on QM9, GEOM-Drugs, and B3LYP, plus strong functional-group-condi...

  8. A Benchmark for Quantum Chemistry Relaxations via Machine Learning Interatomic Potentials

    q-bio.QM 2025-06 conditional novelty 6.0 of 10

    PubChemQCR is a large public dataset of DFT-based molecular relaxation trajectories with energy and force labels, benchmarked with nine machine learning interatomic potentials.

  9. Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Removing explicit noise-level conditioning from graph diffusion models is often harmless, and the paper gives concentration and error-propagation bounds explaining why, with supporting experiments on QM9 and soc-Epinions1.

  10. A Deep Generative Model for the Simulation of Discrete Karst Networks

    stat.ML 2025-06 conditional novelty 5.0 of 10

    A two-step pipeline of a graph recurrent network and a graph denoising diffusion model learns to generate stochastic discrete karst networks from subgraphs of two mapped cave systems, reproducing most geometric and to...

Pith tools