REVIEW 6 cited by
Geometric Algebra Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Problems involving geometric data arise in physics, chemistry, robotics, computer vision, and many other fields. Such data can take numerous forms, for instance points, direction vectors, translations, or rotations, but to date there is no single architecture that can be applied to such a wide variety of geometric types while respecting their symmetries. In this paper we introduce the Geometric Algebra Transformer (GATr), a general-purpose architecture for geometric data. GATr represents inputs, outputs, and hidden states in the projective geometric (or Clifford) algebra, which offers an efficient 16-dimensional vector-space representation of common geometric objects as well as operators acting on them. GATr is equivariant with respect to E(3), the symmetry group of 3D Euclidean space. As a Transformer, GATr is versatile, efficient, and scalable. We demonstrate GATr in problems from n-body modeling to wall-shear-stress estimation on large arterial meshes to robotic motion planning. GATr consistently outperforms both non-geometric and equivariant baselines in terms of error, data efficiency, and scalability.
Forward citations
Cited by 6 Pith papers
-
Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems
Pointwise metrics compress marginal spectra in multimodal inverse problems, and a three-part protocol using CRPS, spectrum fidelity, and calibration reverses model rankings on synthetic and particle-physics benchmarks.
-
Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers for Cosmological Velocity Reconstruction
Velocityformer achieves 35% higher velocity correlation than linear theory by matching graph transformer inductive bias to the line-of-sight broken symmetry and conditioning on long-wavelength physics, while training ...
-
Geometric algebra as the input language of collider foundation models
Collider events are represented as multivectors in Cl(1,3) ⊗ V_flav whose grade projections recover standard observables, intended as input for equivariant foundation models.
-
ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
ATOM is a quasi-equivariant transformer neural operator pretrained on the TG80 dataset that achieves SOTA single-task MD performance and strong zero-shot generalization to unseen molecules and time horizons.
-
Platonic Transformers: A Solid Choice For Equivariance
Platonic Transformers achieve exact equivariance to translations plus discrete Platonic-solid rotations by lifting features into multiple reference frames and sharing one RoPE attention across them, with a linear-time...
-
What Do Lorentz-Equivariant Jet Taggers Learn?
Equivariant jet taggers suppress frame-dependent pseudorapidity while encoding jet mass and N-subjettiness strongly, with bivector channels negligible and vector channels dominant for top tagging.
Discussion (0). Sign in to comment.