Project AURIONAI Use-Cases Research & Innovation
University of Oxford
scientificfamily

SE(3)-Transformer

Self-attention module for 3D point clouds and graphs that is equivariant to rotations and translations. Paper by Fuchs et al. (2020); NVIDIA Deep Learning Examples publish trained checkpoints on NGC.

University of OxfordUniversity of OxfordBoschBoschGermany
Figure from the SE(3)-Transformer paper: Updating the node features using our equivariant attention mechanism in four steps.
Levelfamily
Classscientific
Parametersnot in the notes
Contextnot in the notes
Released18 Jun 2020
Opennessunknown
Runs onnot in the notes
Statusactive

R&D Topics

Equivariant graph networks for moleculesproduced by

Identity

Developer
University of Oxford, Bosch
Family
not in the notes
Released
18 Jun 2020 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
GNN Roto-translation equivariant attention on 3D point clouds and graphs
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
molecule
Output
molecule
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2006.10503 https://arxiv.org/abs/2006.10503
  2. catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/se3transformer__... https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/se3transformer__pyt_ckpt_mode-homo
  3. arxiv.org/html/2006.10503 https://arxiv.org/html/2006.10503

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SE(3)-Transformer", https://aurion.semai.id/models/se3-transformer/, records of October 2026.