Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers

1 April 2023

Papers citing "Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers"

7 / 7 papers shown

Title
Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation Max Gupta Sunayana Rane R. Thomas McCoy Thomas L. Griffiths SSL OOD DRL 182 0 0 29 Mar 2025
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models Yukang Yang Declan Campbell Kaixuan Huang Mengdi Wang Jonathan D. Cohen Taylor Webb LRM 67 2 0 27 Feb 2025
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures Awni Altabaa John Lafferty 37 3 0 26 May 2024
Approximation of relation functions and attention mechanisms Awni Altabaa John Lafferty 30 6 0 13 Feb 2024
Learning Hierarchical Relational Representations through Relational Convolutions Awni Altabaa John Lafferty 30 2 0 05 Oct 2023
The Relational Bottleneck as an Inductive Bias for Efficient Abstraction Taylor Webb Steven M. Frankland Awni Altabaa Simon N. Segert Kamesh Krishnamurthy ... Tyler Giallanza Zack Dulberg Randall O'Reilly John Lafferty Jonathan D. Cohen 34 27 0 12 Sep 2023
Emergent Symbols through Binding in External Memory Taylor Webb I. Sinha J. Cohen 67 64 0 29 Dec 2020