Papers › Generative Modeling on Lie Groups via Euclidean Generalized Score Matching
Generative Modeling on Lie Groups via Euclidean Generalized Score Matching
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.
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):
get_harvested_code_for_paper(arxiv_id="2502.02513")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2502.02513", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2502.02513")
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.
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.
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.
914f2bbd56ed0c20 · report
fixture: signature axis_angle:Tensor/2/float · returned Tensor · level recorded 2026-09-22 e79a535a0171afe6 · report
fixture: signature axis_angle:Tensor/2/float · returned Tensor · level recorded 2026-09-22 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 757d8fbfcc15222b · report
fixture: signature quaternions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 87d39d0333f7619e · report
fixture: signature A:Tensor/2/float, B:Tensor/2/float · returned tuple · level recorded 2026-09-22 89d66ab8c231b799 · report
fixture: returned BackboneUpdate · level recorded 2026-09-22 149672794a6ce709 · report
fixture: returned EdgeTransition · level recorded 2026-09-22 b385876410970ada · report
fixture: returned StructureModuleTransition · level recorded 2026-09-22 e673b21f3beecd05 · report
fixture: returned TorsionAngles · level recorded 2026-09-22 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 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 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 8a3167dc8230216b · report
fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-22 49fba1a002800760 · report
fixture: signature rot_mat:Tensor/3/float · returned Tensor · level recorded 2026-09-22 7504b8f0badd29b3 · report
fixture: signature quat1:Tensor/2/float, quat2:Tensor/2/float · returned Tensor · level recorded 2026-09-22 7d8488e4260d21b8 · report
fixture: signature quat:Tensor/2/float, vec:Tensor/2/float · returned Tensor · level recorded 2026-09-22 075f5885f662efa7 · report
fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-22 2e879b992afd2e24 · report
fixture: signature a:Tensor/3/float, b:Tensor/3/float · returned Tensor · level recorded 2026-09-22 2892b10c249d305e · report
fixture: signature rot:Tensor/3/float · returned Tensor · level recorded 2026-09-22 8f2b10d716763add · report
fixture: signature r:Tensor/3/float, t:Tensor/2/float · returned Tensor · level recorded 2026-09-22 dfce785d0ad4df3b · 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
- IpaScore entry · level 0 · unverified ·
0ff59b29cf0ab633 - BackboneUpdate model · level 1 · ran ·
89d66ab8c231b799 - EdgeTransition helper · level 1 · ran ·
149672794a6ce709 - InvariantPointAttention model · level 0 · unverified ·
dfce785d0ad4df3b - Linear helper · level 1 · ran ·
d3ad22a7f9c56f53 - Rigid helper · level 0 · unverified ·
ec6868fba749c722 - StructureModuleTransition helper · level 1 · ran ·
b385876410970ada - TorsionAngles helper · level 1 · ran ·
e673b21f3beecd05 - flatten_final_dims helper · level 1 · ran · our draft was wrong ·
706bd906bbbd5b15 - ipa_point_weights_init_ helper · level 0 · unverified ·
fcb2f4de473c1b1f - permute_final_dims helper · level 1 · ran · our draft was wrong ·
c653d7a1bb820cd6 - final_init_ helper · level 0 · unverified ·
a10b543dd71d1e5b - gating_init_ helper · level 0 · unverified ·
1336281a5bb9480a - glorot_uniform_init_ helper · level 0 · unverified ·
50401de5c99d7396 - he_normal_init_ helper · level 0 · unverified ·
8a0d47ceb85c9840 - lecun_normal_init_ helper · level 0 · unverified ·
3569de993ea5cde4 - normal_init_ helper · level 0 · unverified ·
b026377d7b0a114f - Rotation helper · level 0 · unverified ·
de43748820aede00 - identity_trans helper · level 1 · ran · our draft was wrong ·
ca30dcd53a3e6051 - rot_matmul helper · level 1 · ran · our draft was wrong ·
2e879b992afd2e24 - rot_vec_mul helper · level 1 · ran · our draft was wrong ·
8f2b10d716763add - trunc_normal_init_ helper · level 0 · unverified ·
54e19d7f047b2518 - identity_quats helper · level 1 · ran · our draft was wrong ·
0ed21f60eea50f93 - identity_rot_mats helper · level 1 · ran · our draft was wrong ·
1af8886de7bf2f78 - invert_quat helper · level 1 · ran · our draft was wrong ·
8a3167dc8230216b - invert_rot_mat helper · level 1 · ran · violated contract ·
49fba1a002800760 - quat_multiply helper · level 1 · ran · our draft was wrong ·
7504b8f0badd29b3 - quat_multiply_by_vec helper · level 1 · ran · our draft was wrong ·
7d8488e4260d21b8 - quat_to_rot helper · level 1 · ran · our draft was wrong ·
075f5885f662efa7 - rot_to_quat helper · level 1 · ran; the contract check could not run (RAISES) ·
2892b10c249d305e - _calculate_fan helper · level 1 · ran; the contract check could not run ·
e6c1f4ae2bdfd63e - _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
- modify_conformer entry · level 0 · unverified ·
eb444236e23ac6f3 - axis_angle_to_matrix helper · level 1 · ran · our draft was wrong ·
914f2bbd56ed0c20 - modify_conformer_torsion_angles helper · level 1 · ran · our draft was wrong ·
35c7828fc29cfeec - rigid_transform_Kabsch_3D_torch helper · level 1 · ran; the contract check could not run (RAISES) ·
87d39d0333f7619e - axis_angle_to_quaternion helper · level 1 · ran · our draft was wrong ·
e79a535a0171afe6 - 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
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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