Versor: A Geometric Sequence Architecture

TL;DR

Versor introduces a geometric sequence architecture using Conformal Geometric Algebra, achieving superior performance, interpretability, and efficiency across diverse tasks compared to traditional neural network models.

Contribution

The paper presents Versor, a novel geometric sequence architecture leveraging CGA for improved generalization, interpretability, and efficiency, with new mechanisms like RRA and GPA for scalable relational modeling.

Findings

Outperforms Transformers and GNNs on multiple benchmarks

Uses significantly fewer parameters (up to 200x less)

Maintains stable out-of-distribution predictions

Abstract

A novel sequence architecture is introduced, Versor, which uses Conformal Geometric Algebra (CGA) in place of traditional linear operations to achieve structural generalization and significant performance improvements on a variety of tasks, while offering improved interpretability and efficiency. By embedding states in the $Cl_{4,1}$ manifold and evolving them via geometric transformations (rotors), Versor natively represents $SE(3)$-equivariant relationships without requiring explicit structural encoding. Versor is validated on chaotic N-body dynamics, topological reasoning, and standard multimodal benchmarks (CIFAR-10, WikiText-103), consistently outperforming Transformers, Graph Networks, and geometric baselines (GATr, EGNN). Key results include: orders-of-magnitude fewer parameters ($200\times$ vs. Transformers); interpretable attention decomposing into proximity and orientational components; zero-shot scale generalization (0.993 vs. 0.070 MCC for ViT); and featuring a Recursive Rotor Accumulator (RRA) for $O(L)$ linear temporal complexity in dynamical systems, and a Geometric Product Attention (GPA) mechanism for $O(L^{2})$ global relational modeling, allowing for task-specific architectural pruning or hybridization depending on the required scale. In out-of-distribution tests, Versor maintains stable predictions while Transformers fail catastrophically. Custom Clifford kernels achieve a cumulative over $100\times$ speedup via bit-masked contraction and specialized Matrix Isomorphism kernels, reducing per-step latency to 1.05 ms and outperforming highly-optimized Transformer baselines.