3 papers
cs.AI2026
Geodesic Flow Matching for Denoising High-Dimensional Structured Representations
Karim Habashy, Chris Eliasmith
Vector Symbolic Algebras (VSAs) enable robust neurosymbolic reasoning by encoding symbolic information into high-dimensional distributed representations. For continuous domains, Sp…
cs.AI2025
Vector Symbolic Algebras for the Abstraction and Reasoning Corpus
Isaac Joffe, Chris Eliasmith
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AG…
cs.LG2025
Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
Varun Dhanraj, Chris Eliasmith
Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical…