Papers › Geometric Latent Diffusion Models for 3D Molecule Generation

Geometric Latent Diffusion Models for 3D Molecule Generation

2 May 2023arXiv:2305.01140archive 2025-07-28

Minkai Xu, Alexander Powers, Ron Dror, Stefano Ermon, Jure Leskovec

Generative models, especially diffusion models (DMs), have achieved promising results for generating feature-rich geometries and advancing foundational science problems such as molecule design. Inspired by the recent huge success of Stable (latent) Diffusion models, we propose a novel and principled method for 3D molecule generation named Geometric Latent Diffusion Models (GeoLDM). GeoLDM is the first latent DM model for the molecular geometry domain, composed of autoencoders encoding structures into continuous latent codes and DMs operating in the latent space. Our key innovation is that for modeling the 3D molecular geometries, we capture its critical roto-translational equivariance constraints by building a point-structured latent space with both invariant scalars and equivariant tensors. Extensive experiments demonstrate that GeoLDM can consistently achieve better performance on multiple molecule generation benchmarks, with up to 7\% improvement for the valid percentage of large biomolecules. Results also demonstrate GeoLDM's higher capacity for controllable generation thanks to the latent modeling. Code is provided at \url{https://github.com/MinkaiXu/GeoLDM}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.01140")

Code

Syntology Ran 4 of 9 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 2 ran; community (archive-listed): 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

minkaixu/geoldm officialmentioned in papermentioned on GitHubpytorchMIT report
rlacombe/accgeoldm mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 4 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
3ran
5unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

random_rotation minkaixu/geoldm/utils.py official repository ran fingerprinted MIT (permissive) · e372872a463628a7 · report
unsorted_segment_sum minkaixu/geoldm/egnn/egnn.py official repository ran · our draft was wrong MIT (permissive) · dfdf6dc1a0720e57 · report
get_dataset_info minkaixu/geoldm/configs/datasets_config.py official repository unverified MIT (permissive) · 6ee9e481f2c35447 · report
gradient_clipping minkaixu/geoldm/utils.py official repository unverified MIT (permissive) · e033860884ced8ac · report
load_model minkaixu/geoldm/utils.py official repository unverified MIT (permissive) · fc4da23dd75dcb46 · report
load_split_data minkaixu/geoldm/build_geom_dataset.py official repository unverified MIT (permissive) · edf83b952680cf55 · report
compute_loss_and_nll rlacombe/accgeoldm/qm9/losses.py community (archive-listed) ran MIT (permissive) · 4ed06d5114046b7e · report
sum_except_batch rlacombe/accgeoldm/qm9/losses.py community (archive-listed) ran fingerprinted MIT (permissive) · 90c529ca8e85d3db · report
get_args_gen rlacombe/accgeoldm/eval_conditional_qm9.py community (archive-listed) unverified MIT (permissive) · f576c0a0e0ae29c2 · report

Tasks

3D Molecule GenerationUnconditional Molecule Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unconditional Molecule Generation QM9 GeoLDM Validity 93.80 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections