Papers › LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space

LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space

28 May 2024arXiv:2405.17829archive 2025-07-28

Jinho Chang, Jong Chul Ye

With the emergence of diffusion models as the frontline of generative models, many researchers have proposed molecule generation techniques with conditional diffusion models. However, the unavoidable discreteness of a molecule makes it difficult for a diffusion model to connect raw data with highly complex conditions like natural language. To address this, we present a novel latent diffusion model dubbed LDMol for text-conditioned molecule generation. LDMol comprises a molecule autoencoder that produces a learnable and structurally informative feature space, and a natural language-conditioned latent diffusion model. In particular, recognizing that multiple SMILES notations can represent the same molecule, we employ a contrastive learning strategy to extract feature space that is aware of the unique characteristics of the molecule structure. LDMol outperforms the existing baselines on the text-to-molecule generation benchmark, suggesting a potential for diffusion models can outperform autoregressive models in text data generation with a better choice of the latent domain. Furthermore, we show that LDMol can be applied to downstream tasks such as molecule-to-text retrieval and text-guided molecule editing, demonstrating its versatility as a diffusion model.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples: 8 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 9: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

jinhojsk515/ldmol officialmentioned on GitHubpytorchSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified 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: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
4ran
3unverified

Licence: 1 of the 9 samples is 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 jinhojsk515/ldmol. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jinhojsk515/ldmol official repository 8 samples, 5 ran (0 instrument-failed) · 3 unverified
CrossAttention in 85 papers models.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 97fc89954c17d8f4 · report fixture: returned CrossAttention · level recorded 2026-09-22
FinalLayer in 29 papers models.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 790db4e566777808 · report fixture: returned FinalLayer · level recorded 2026-09-22
LabelEmbedder in 13 papers models.py ran Apache-2.0 (permissive) · 9d9a29443412f3ad · report fixture: signature labels:Tensor/1/int, train:bool/0/bool, force_drop_ids:NoneType/0/? · returned Tensor · level recorded 2026-09-24
TimestepEmbedder in 27 papers
census: 9 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
models.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 36e69cc6393e3e74 · report fixture: signature t:Tensor/1/int · returned Tensor · level recorded 2026-09-22
get_2d_sincos_pos_embed in 170 papers models.py ran · honoured contract Apache-2.0 (permissive) · bf3a0284f8d7cc37 · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool, extra_tokens:int/0/int · returned ndarray · level recorded 2026-09-22
DiT in 10 papers models.py unverified Apache-2.0 (permissive) · 5648b79269afe02f · report
DiTBlock in 17 papers models.py unverified Apache-2.0 (permissive) · edd1b87aa37672af · report
LDMol models.py unverified Apache-2.0 (permissive) · 466c4f13f935fd40 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 03310bba324ae4fb · report fixture: signature x:Tensor/2/float, shift:Tensor/1/float, scale:Tensor/1/float · returned Tensor · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LDMol (graph method: LDMol). 10 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. LDMol entry · level 0 · unverified · 466c4f13f935fd40
  2. DiT model · level 0 · unverified · 5648b79269afe02f
  3. DiTBlock model · level 0 · unverified · edd1b87aa37672af
  4. FinalLayer model · level 1 · ran · 790db4e566777808
  5. LabelEmbedder helper · level 1 · ran · 9d9a29443412f3ad
  6. TimestepEmbedder model · level 1 · ran · 36e69cc6393e3e74
  7. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · bf3a0284f8d7cc37
  8. CrossAttention model · level 1 · ran · 97fc89954c17d8f4
  9. modulate helper · level 1 · ran · our draft was wrong · 03310bba324ae4fb
  10. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · e5947aba1d10885f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.17829") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningDecoderText RetrievalText-based de novo Molecule Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-based de novo Molecule Generation ChEBI-20 LDMol BLEU 92.6 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol Exact Match 53.3 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol Frechet ChemNet Distance (FCD) 0.20 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol Levenshtein 6.750 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol MACCS FTS 97.3 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol Morgan FTS 93.1 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol RDK FTS 95.0 #1 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 LDMol Validity 94.1 #1 of 20 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

AWAREAbsolute Position EncodingsAdamAttentionBPEContrastive LearningDense ConnectionsDiffusionDropoutLabel SmoothingLatent Diffusion ModelLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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