Papers › Text-Guided Molecule Generation with Diffusion Language Model

Text-Guided Molecule Generation with Diffusion Language Model

20 Feb 2024arXiv:2402.13040archive 2025-07-28

Haisong Gong, Qiang Liu, Shu Wu, Liang Wang

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods. TGM-DLM updates token embeddings within the SMILES string collectively and iteratively, using a two-phase diffusion generation process. The first phase optimizes embeddings from random noise, guided by the text description, while the second phase corrects invalid SMILES strings to form valid molecular representations. We demonstrate that TGM-DLM outperforms MolT5-Base, an autoregressive model, without the need for additional data resources. Our findings underscore the remarkable effectiveness of TGM-DLM in generating coherent and precise molecules with specific properties, opening new avenues in drug discovery and related scientific domains. Code will be released at: https://github.com/Deno-V/tgm-dlm.

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 21 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 14 ran (6 with no instrument failure; 8 where Syntology's instrument failed). 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. 2 of the 14 samples that ran have no recorded date.

deno-v/tgm-dlm officialmentioned in papermentioned on GitHubjaxSyntology: 21 samples, 14 ran (8 instrument-failed) · 7 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

21 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
8ran · our draft was wrong
4ran
7unverified

Licence: 21 of the 21 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 deno-v/tgm-dlm. “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”. “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.

deno-v/tgm-dlm official repository 21 samples, 14 ran (8 instrument-failed) · 7 unverified
BertSelfOutput in 14 papers improved-diffusion/improved_diffusion/transformer_model.py ran · metamorphic tier: invariant no licence file found · pointer only · b628485b4544176e · report fixture: signature hidden_states:Tensor/2/float, input_tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Upsample in 77 papers improved-diffusion/improved_diffusion/transformer_model.py ran fingerprinted no licence file found · pointer only · 14e6a43c9ced2404 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
approx_standard_normal_cdf in 150 papers
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
improved-diffusion/improved_diffusion/losses.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cfd76fd0d89574a4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
discretized_gaussian_log_likelihood in 124 papers
census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
improved-diffusion/improved_diffusion/losses.py ran · our draft was wrong no licence file found · pointer only · cd33283d615fb3d7 · report fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded, date not recorded
find_pruneable_heads_and_indices in 19 papers improved-diffusion/improved_diffusion/transformer_model.py ran · our draft was wrong no licence file found · pointer only · ffe4fa9032a930ff · report fixture: signature heads:list/1/int, n_heads:int/0/int, head_size:int/0/int, already_pruned_heads:set/0/? · returned tuple · level recorded 2026-09-22
generate_samples in 16 papers improved-diffusion/control_gen/baseline_control.py ran no licence file found · pointer only · bd70407415c5ed19 · report fixture: signature args:Args/0/?, prompt:Tensor/2/int, model:callable/0/?, tokenizer:MinimalTokenizer/0/? · returned list · level recorded 2026-09-24
layer_norm in 32 papers improved-diffusion/improved_diffusion/transformer_model.py ran · our draft was wrong no licence file found · pointer only · 8347681d84656d7d · report fixture: signature hidden_size:int/0/int · returned LayerNorm · level recorded 2026-09-22
levenshteinDistance improved-diffusion/control_gen/eval_control.py ran · honoured contract fingerprinted no licence file found · pointer only · ee1169ece28e0d9d · report fixture: signature s1:str/0/str, s2:str/0/str · returned int · level recorded 2026-09-24
load_results_simple improved-diffusion/anlg_infill/mbr_eval.py ran · our draft was wrong no licence file found · pointer only · 6690b1379e201b37 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
mbr improved-diffusion/anlg_infill/mbr_eval.py ran no licence file found · pointer only · 23e6db3ffd64425a · report fixture: signature result_lst:list/1/ndarray, total_len:int/0/int, sample_size:int/0/int, utility:callable/0/? · returned list · level recorded 2026-09-24
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
improved-diffusion/improved_diffusion/losses.py ran · honoured contract fingerprinted no licence file found · pointer only · cf2798b666b231ca · report fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
prune_linear_layer in 40 papers improved-diffusion/improved_diffusion/transformer_model.py ran · our draft was wrong no licence file found · pointer only · 63bf3ad9c297ab92 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
remove_leaves improved-diffusion/control_gen/baseline_control.py ran · our draft was wrong no licence file found · pointer only · 8fc7161a00ae39b0 · report fixture: signature tree_:Tree/1/Tree · returned Tree · level recorded 2026-09-24
trans_nd improved-diffusion/improved_diffusion/transformer_model.py ran · our draft was wrong no licence file found · pointer only · 0fa17cc15d81b5a7 · report fixture: signature config:Config/0/?, hidden_size:int/0/int, num_attention_heads:int/0/int, attention_head_size:int/0/int · returned BertSelfAttention · level recorded 2026-09-22
BertAttention in 28 papers improved-diffusion/improved_diffusion/transformer_model.py unverified no licence file found · pointer only · 95d638062692e25c · report
BertSelfAttention in 29 papers improved-diffusion/improved_diffusion/transformer_model.py unverified no licence file found · pointer only · c52c56e6b503ff9a · report
Downsample in 58 papers improved-diffusion/improved_diffusion/transformer_model.py unverified no licence file found · pointer only · 6217144fde18c480 · report
TransUNetModel improved-diffusion/improved_diffusion/transformer_model.py unverified no licence file found · pointer only · 4aabdb4f1e27436a · report
TransformerBlock in 73 papers improved-diffusion/improved_diffusion/transformer_model.py unverified no licence file found · pointer only · 85f117cd2c476a03 · report
generate_samples_from_scratch improved-diffusion/control_gen/baseline_control.py unverified no licence file found · pointer only · cc6bf6f3b1388227 · report
get_smis ev.py unverified no licence file found · pointer only · 9f87c93b00243392 · report

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 Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM) (graph method: Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM)). 22 bricks; individually on a fixture: 10 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. TransUNetModel entry · level 0 · unverified · 4aabdb4f1e27436a
  2. Downsample model · level 0 · unverified · 6217144fde18c480
  3. SiLU helper · level 1 · ran · 5465fa33e2f8631e
  4. TimestepEmbedSequential model · level 0 · unverified · ed74c5af0b1d1d51
  5. TransformerBlock model · level 0 · unverified · 85f117cd2c476a03
  6. Upsample model · level 1 · ran · 14e6a43c9ced2404
  7. convert_module_to_f16 helper · level 0 · unverified · f4dd78dce0a9bc88
  8. convert_module_to_f32 helper · level 0 · unverified · 6ae95f4d952ed88c
  9. layer_norm helper · level 1 · ran · our draft was wrong · 8347681d84656d7d
  10. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  11. timestep_embedding helper · level 1 · ran · our draft was wrong · 88867f4df8cef2a9
  12. trans_nd helper · level 1 · ran · our draft was wrong · 0fa17cc15d81b5a7
  13. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  14. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  15. TimestepBlock model · level 0 · unverified · 40fb9bc947892adc
  16. BertAttention helper · level 0 · unverified · 95d638062692e25c
  17. checkpoint helper · level 0 · unverified · fb150e1f7e53041e
  18. BertSelfAttention helper · level 0 · unverified · c52c56e6b503ff9a
  19. BertSelfOutput helper · level 1 · ran · b628485b4544176e
  20. find_pruneable_heads_and_indices helper · level 1 · ran · our draft was wrong · ffe4fa9032a930ff
  21. prune_linear_layer helper · level 1 · ran · our draft was wrong · 63bf3ad9c297ab92
  22. CheckpointFunction helper · level 1 · ran · 27faeacc0d8cf344

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="2402.13040") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Drug DiscoveryLanguage ModelingLanguage ModellingText-based de novo Molecule Generationmodel

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr BLEU 82.8 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Exact Match 24.2 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Frechet ChemNet Distance (FCD) 0.89 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Levenshtein 16.897 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr MACCS FTS 87.4 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Morgan FTS 72.2 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Parameter Count 180000000 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr RDK FTS 77.1 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Text2Mol 58.9 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM w/o corr Validity 78.9 #8 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM BLEU 82.6 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Exact Match 24.2 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Frechet ChemNet Distance (FCD) 0.77 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Levenshtein 17.003 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM MACCS FTS 85.4 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Morgan FTS 68.8 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Parameter Count 180000000 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM RDK FTS 73.9 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Text2Mol 58.1 #9 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 TGM-DLM Validity 87.1 #9 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

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