Papers › Fast 3D Molecule Generation via Unified Geometric Optimal Transport

Fast 3D Molecule Generation via Unified Geometric Optimal Transport

24 May 2024arXiv:2405.15252archive 2025-07-28

Haokai Hong, WanYu Lin, Kay Chen Tan

This paper proposes a new 3D molecule generation framework, called GOAT, for fast and effective 3D molecule generation based on the flow-matching optimal transport objective. Specifically, we formulate a geometric transport formula for measuring the cost of mapping multi-modal features (e.g., continuous atom coordinates and categorical atom types) between a base distribution and a target data distribution. Our formula is solved within a unified, equivalent, and smooth representation space. This is achieved by transforming the multi-modal features into a continuous latent space with equivalent networks. In addition, we find that identifying optimal distributional coupling is necessary for fast and effective transport between any two distributions. We further propose a flow refinement and purification mechanism for optimal coupling identification. By doing so, GOAT can turn arbitrary distribution couplings into new deterministic couplings, leading to a unified optimal transport path for fast 3D molecule generation. The purification filters the subpar molecules to ensure the ultimate generation performance. We theoretically prove the proposed method indeed reduced the transport cost. Finally, extensive experiments show that GOAT enjoys the efficiency of solving geometric optimal transport, leading to a double speedup compared to the sub-optimal method while achieving the best generation quality regarding validity, uniqueness, and novelty.

PaperPDFCode 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.

Syntology holds a reference implementation of GOAT, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='GOAT') (how to connect); the free check have('2405.15252') needs no token.

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

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 16 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 20 samples from 1 repository, 16 ran (9 with no instrument failure; 7 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

HaokaiHong/GOAT found in paper text by SyntologySyntology: 20 samples, 16 ran (7 instrument-failed) · 4 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

20 samples harvested: 16 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 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.

4ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
4ran
4unverified

Licence: 20 of the 20 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 HaokaiHong/GOAT. “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.

HaokaiHong/GOAT found in paper text by Syntology 20 samples, 16 ran (7 instrument-failed) · 4 unverified
EquivariantUpdate models/goat.py ran no licence file found · pointer only · a7469529035aa9ae · report fixture: returned EquivariantUpdate · level recorded 2026-09-22
GCL models/goat.py ran no licence file found · pointer only · 70a5867a1216b27a · report fixture: returned GCL · level recorded 2026-09-22
GNN in 23 papers models/goat.py ran no licence file found · pointer only · d6b4d81e5c7eb060 · report fixture: returned GNN · level recorded 2026-09-22
SinusoidsEmbeddingNew models/goat.py ran no licence file found · pointer only · c337a600bec8d2e1 · report fixture: returned SinusoidsEmbeddingNew · level recorded 2026-09-22
T in 9 papers models/goat.py ran · honoured contract no licence file found · pointer only · b7c96c37f7279a53 · report fixture: signature t:Tensor/0/float · returned Tensor · level recorded 2026-09-22
T_hat models/goat.py ran · honoured contract fingerprinted no licence file found · pointer only · da6d6467ef1f6a2d · report fixture: signature t:float/0/float · returned float · level recorded 2026-09-22
best_fit_transform models/goat.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9e5605e920450c4e · report fixture: signature A:ndarray/2/float, B:ndarray/2/float · returned tuple · level recorded 2026-09-22
coord2diff in 7 papers models/goat.py ran; the contract check could not run (RAISES) no licence file found · pointer only · e9fb6b7c8ea39384 · report fixture: signature x:Tensor/2/float, edge_index:tuple/1/Tensor, norm_constant:int/0/int · returned tuple · level recorded 2026-09-22
get_assignments models/goat.py ran · violated contract fingerprinted no licence file found · pointer only · 0b8ad1458eb20807 · report fixture: signature src:ndarray/2/float, dst:ndarray/2/float · returned tuple · level recorded 2026-09-22
icp models/goat.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 33789bda1e02793c · report fixture: signature A:ndarray/2/float, B:ndarray/2/float, max_iterations:int/0/int, tolerance:float/0/float · returned tuple · level recorded 2026-09-22
loss_reduce_mean_except_batch_with_mask models/goat.py ran · honoured contract no licence file found · pointer only · 72ef88d3157bc2f0 · report fixture: signature loss:Tensor/3/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-22
polynomial_schedule_ models/goat.py ran · honoured contract fingerprinted no licence file found · pointer only · 7b7df21a86fb73fe · report fixture: signature t:Tensor/0/float, s:float/0/float, power:float/0/float · returned Tensor · level recorded 2026-09-22
remove_mean in 8 papers models/goat.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cfb922542fc1b6d0 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
remove_mean_with_mask in 6 papers models/goat.py ran · our draft was wrong no licence file found · pointer only · 324f8277ebc8ccb8 · report fixture: signature x:Tensor/3/float, node_mask:Tensor/3/float · returned Tensor · level recorded 2026-09-22
sum_except_batch in 25 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
models/goat.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 076381011e4298d5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unsorted_segment_sum in 33 papers models/goat.py ran · our draft was wrong no licence file found · pointer only · d96ea1a7adc8e5bb · report fixture: signature data:Tensor/2/float, segment_ids:Tensor/1/int, num_segments:int/0/int, normalization_factor:float/0/float, aggregation_method:str/0/str · returned Tensor · level recorded 2026-09-22
EGNN models/goat.py unverified no licence file found · pointer only · 231100014c9c90e6 · report
EGNN_dynamics models/goat.py unverified no licence file found · pointer only · b492c97ab6da5e67 · report
EquivariantBlock models/goat.py unverified no licence file found · pointer only · ef4aca87fa8123a6 · report
GeometricOptimalTransportFlow models/goat.py unverified no licence file found · pointer only · c9411f5bc013ac21 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for GOAT (graph method: GOAT), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. flow_matching_loss entry · level 2 · ran · our draft was wrong · 88d57f1a5e21721393750892132e8dcd53c6209ce2f71eb413a6f25e7223a19a

harvested Assembly for GOAT (graph method: GOAT). 21 bricks; individually on a fixture: 17 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. GeometricOptimalTransportFlow entry · level 0 · unverified · c9411f5bc013ac21
  2. EGNN_dynamics helper · level 0 · unverified · b492c97ab6da5e67
  3. T scheduler · level 1 · ran · honoured contract · b7c96c37f7279a53
  4. T_hat scheduler · level 1 · ran · honoured contract · da6d6467ef1f6a2d
  5. icp helper · level 1 · ran · our draft was wrong · 33789bda1e02793c
  6. loss_reduce_mean_except_batch_with_mask loss · level 1 · ran · honoured contract · 72ef88d3157bc2f0
  7. pad_t_like_x helper · level 1 · ran · our draft was wrong · 9e320fdaa5a3063f
  8. polynomial_schedule_ scheduler · level 1 · ran · honoured contract · 7b7df21a86fb73fe
  9. sum_except_batch helper · level 1 · ran · our draft was wrong · 076381011e4298d5
  10. EGNN helper · level 0 · unverified · 231100014c9c90e6
  11. GNN helper · level 1 · ran · d6b4d81e5c7eb060
  12. remove_mean helper · level 1 · ran · our draft was wrong · cfb922542fc1b6d0
  13. remove_mean_with_mask helper · level 1 · ran · our draft was wrong · 324f8277ebc8ccb8
  14. best_fit_transform helper · level 1 · ran · our draft was wrong · 9e5605e920450c4e
  15. get_assignments helper · level 1 · ran · violated contract · 0b8ad1458eb20807
  16. EquivariantBlock helper · level 0 · unverified · ef4aca87fa8123a6
  17. SinusoidsEmbeddingNew helper · level 1 · ran · c337a600bec8d2e1
  18. coord2diff helper · level 1 · ran; the contract check could not run (RAISES) · e9fb6b7c8ea39384
  19. GCL helper · level 1 · ran · 70a5867a1216b27a
  20. EquivariantUpdate helper · level 1 · ran · a7469529035aa9ae
  21. unsorted_segment_sum helper · level 1 · ran · our draft was wrong · d96ea1a7adc8e5bb

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="2405.15252") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Molecule Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

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