Papers › Generative Modeling on Lie Groups via Euclidean Generalized Score Matching

Generative Modeling on Lie Groups via Euclidean Generalized Score Matching

4 Feb 2025arXiv:2502.02513archive 2025-07-28

Marco Bertolini, Tuan Le, Djork-Arné Clevert

We extend Euclidean score-based diffusion processes to generative modeling on Lie groups. Through the formalism of Generalized Score Matching, our approach yields a Langevin dynamics which decomposes as a direct sum of Lie algebra representations, enabling generative processes on Lie groups while operating in Euclidean space. Unlike equivariant models, which restrict the space of learnable functions by quotienting out group orbits, our method can model any target distribution on any (non-Abelian) Lie group. Standard score matching emerges as a special case of our framework when the Lie group is the translation group. We prove that our generalized generative processes arise as solutions to a new class of paired stochastic differential equations (SDEs), introduced here for the first time. We validate our approach through experiments on diverse data types, demonstrating its effectiveness in real-world applications such as SO(3)-guided molecular conformer generation and modeling ligand-specific global SE(3) transformations for molecular docking, showing improvement in comparison to Riemannian diffusion on the group itself. We show that an appropriate choice of Lie group enhances learning efficiency by reducing the effective dimensionality of the trajectory space and enables the modeling of transitions between complex data distributions. Additionally, we demonstrate the universality of our approach by deriving how it extends to flow matching.

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.

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

Code

Syntology 25 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 15 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 13 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 25 samples from 2 repositories, 20 ran (5 with no instrument failure; 15 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.

gcorso/DiffDock found in paper text by SyntologySyntology: 6 samples, 5 ran (5 instrument-failed) · 1 unverified report
jasonkyuyim/se3_diffusion found in paper text by SyntologySyntology: 19 samples, 15 ran (10 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

25 samples harvested: 20 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 15 where Syntology's instrument failed) · 5 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 · violated contract
13ran · our draft was wrong
2ran; the contract check could not run
4ran
5unverified

Licence: 0 of the 25 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 3 samples 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.

gcorso/DiffDock found in paper text by Syntology 6 samples, 5 ran (5 instrument-failed) · 1 unverified
axis_angle_to_matrix utils/diffusion_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 914f2bbd56ed0c20 · report fixture: signature axis_angle:Tensor/2/float · returned Tensor · level recorded 2026-09-22
axis_angle_to_quaternion utils/diffusion_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · e79a535a0171afe6 · report fixture: signature axis_angle:Tensor/2/float · returned Tensor · level recorded 2026-09-22
modify_conformer_torsion_angles utils/diffusion_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 35c7828fc29cfeec · report fixture: signature pos:Tensor/2/float, edge_index:Tensor/2/int, mask_rotate:Tensor/2/bool, torsion_updates:ndarray/1/float, as_numpy:bool/0/bool · returned Tensor · level recorded 2026-09-22
quaternion_to_matrix in 10 papers utils/diffusion_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 757d8fbfcc15222b · report fixture: signature quaternions:Tensor/2/float · returned Tensor · level recorded 2026-09-22
rigid_transform_Kabsch_3D_torch utils/diffusion_utils.py ran; the contract check could not run (RAISES) MIT (permissive) · 87d39d0333f7619e · report fixture: signature A:Tensor/2/float, B:Tensor/2/float · returned tuple · level recorded 2026-09-22
modify_conformer utils/diffusion_utils.py unverified MIT (permissive) · eb444236e23ac6f3 · report
jasonkyuyim/se3_diffusion found in paper text by Syntology 19 samples, 15 ran (10 instrument-failed) · 4 unverified
BackboneUpdate model/ipa_pytorch.py ran fingerprinted MIT (permissive) · 89d66ab8c231b799 · report fixture: returned BackboneUpdate · level recorded 2026-09-22
EdgeTransition model/ipa_pytorch.py ran MIT (permissive) · 149672794a6ce709 · report fixture: returned EdgeTransition · level recorded 2026-09-22
StructureModuleTransition model/ipa_pytorch.py ran fingerprinted MIT (permissive) · b385876410970ada · report fixture: returned StructureModuleTransition · level recorded 2026-09-22
TorsionAngles model/ipa_pytorch.py ran fingerprinted MIT (permissive) · e673b21f3beecd05 · report fixture: returned TorsionAngles · level recorded 2026-09-22
identity_quats model/ipa_pytorch.py ran · our draft was wrong MIT (permissive) · 0ed21f60eea50f93 · report fixture: signature batch_dims:tuple/1/int, dtype:dtype/0/?, device:device/0/?, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-22
identity_rot_mats model/ipa_pytorch.py ran · our draft was wrong MIT (permissive) · 1af8886de7bf2f78 · report fixture: signature batch_dims:tuple/1/int, dtype:dtype/0/?, device:device/0/?, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-22
identity_trans model/ipa_pytorch.py ran · our draft was wrong MIT (permissive) · ca30dcd53a3e6051 · report fixture: signature batch_dims:tuple/1/int, dtype:dtype/0/?, device:device/0/?, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-22
invert_quat model/ipa_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 8a3167dc8230216b · report fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-22
invert_rot_mat model/ipa_pytorch.py ran · violated contract fingerprinted MIT (permissive) · 49fba1a002800760 · report fixture: signature rot_mat:Tensor/3/float · returned Tensor · level recorded 2026-09-22
quat_multiply model/ipa_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 7504b8f0badd29b3 · report fixture: signature quat1:Tensor/2/float, quat2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
quat_multiply_by_vec model/ipa_pytorch.py ran · our draft was wrong MIT (permissive) · 7d8488e4260d21b8 · report fixture: signature quat:Tensor/2/float, vec:Tensor/2/float · returned Tensor · level recorded 2026-09-22
quat_to_rot in 6 papers model/ipa_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 075f5885f662efa7 · report fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-22
rot_matmul model/ipa_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 2e879b992afd2e24 · report fixture: signature a:Tensor/3/float, b:Tensor/3/float · returned Tensor · level recorded 2026-09-22
rot_to_quat model/ipa_pytorch.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 2892b10c249d305e · report fixture: signature rot:Tensor/3/float · returned Tensor · level recorded 2026-09-22
rot_vec_mul model/ipa_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 8f2b10d716763add · report fixture: signature r:Tensor/3/float, t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
InvariantPointAttention model/ipa_pytorch.py unverified MIT (permissive) · dfce785d0ad4df3b · report
IpaScore model/ipa_pytorch.py unverified MIT (permissive) · 0ff59b29cf0ab633 · report
Rigid model/ipa_pytorch.py unverified MIT (permissive) · ec6868fba749c722 · report
Rotation model/ipa_pytorch.py unverified MIT (permissive) · de43748820aede00 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for score-based diffusion processes on Lie group representations (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for score-based diffusion processes on Lie group representations (graph method: score-based diffusion processes on Lie group representations). 32 bricks; individually on a fixture: 20 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 13 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. IpaScore entry · level 0 · unverified · 0ff59b29cf0ab633
  2. BackboneUpdate model · level 1 · ran · 89d66ab8c231b799
  3. EdgeTransition helper · level 1 · ran · 149672794a6ce709
  4. InvariantPointAttention model · level 0 · unverified · dfce785d0ad4df3b
  5. Linear helper · level 1 · ran · d3ad22a7f9c56f53
  6. Rigid helper · level 0 · unverified · ec6868fba749c722
  7. StructureModuleTransition helper · level 1 · ran · b385876410970ada
  8. TorsionAngles helper · level 1 · ran · e673b21f3beecd05
  9. flatten_final_dims helper · level 1 · ran · our draft was wrong · 706bd906bbbd5b15
  10. ipa_point_weights_init_ helper · level 0 · unverified · fcb2f4de473c1b1f
  11. permute_final_dims helper · level 1 · ran · our draft was wrong · c653d7a1bb820cd6
  12. final_init_ helper · level 0 · unverified · a10b543dd71d1e5b
  13. gating_init_ helper · level 0 · unverified · 1336281a5bb9480a
  14. glorot_uniform_init_ helper · level 0 · unverified · 50401de5c99d7396
  15. he_normal_init_ helper · level 0 · unverified · 8a0d47ceb85c9840
  16. lecun_normal_init_ helper · level 0 · unverified · 3569de993ea5cde4
  17. normal_init_ helper · level 0 · unverified · b026377d7b0a114f
  18. Rotation helper · level 0 · unverified · de43748820aede00
  19. identity_trans helper · level 1 · ran · our draft was wrong · ca30dcd53a3e6051
  20. rot_matmul helper · level 1 · ran · our draft was wrong · 2e879b992afd2e24
  21. rot_vec_mul helper · level 1 · ran · our draft was wrong · 8f2b10d716763add
  22. trunc_normal_init_ helper · level 0 · unverified · 54e19d7f047b2518
  23. identity_quats helper · level 1 · ran · our draft was wrong · 0ed21f60eea50f93
  24. identity_rot_mats helper · level 1 · ran · our draft was wrong · 1af8886de7bf2f78
  25. invert_quat helper · level 1 · ran · our draft was wrong · 8a3167dc8230216b
  26. invert_rot_mat helper · level 1 · ran · violated contract · 49fba1a002800760
  27. quat_multiply helper · level 1 · ran · our draft was wrong · 7504b8f0badd29b3
  28. quat_multiply_by_vec helper · level 1 · ran · our draft was wrong · 7d8488e4260d21b8
  29. quat_to_rot helper · level 1 · ran · our draft was wrong · 075f5885f662efa7
  30. rot_to_quat helper · level 1 · ran; the contract check could not run (RAISES) · 2892b10c249d305e
  31. _calculate_fan helper · level 1 · ran; the contract check could not run · e6c1f4ae2bdfd63e
  32. _prod helper · level 1 · ran · violated contract · 5fcde0d4e5ddc285

harvested Assembly for score-based diffusion processes on Lie group representations (graph method: score-based diffusion processes on Lie group representations). 6 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. modify_conformer entry · level 0 · unverified · eb444236e23ac6f3
  2. axis_angle_to_matrix helper · level 1 · ran · our draft was wrong · 914f2bbd56ed0c20
  3. modify_conformer_torsion_angles helper · level 1 · ran · our draft was wrong · 35c7828fc29cfeec
  4. rigid_transform_Kabsch_3D_torch helper · level 1 · ran; the contract check could not run (RAISES) · 87d39d0333f7619e
  5. axis_angle_to_quaternion helper · level 1 · ran · our draft was wrong · e79a535a0171afe6
  6. quaternion_to_matrix helper · level 1 · ran · our draft was wrong · 757d8fbfcc15222b

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="2502.02513") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Molecular Docking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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