{"total":30,"rows":[{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178,"area":null},{"id":"2102.10717","title":"Abstraction and Analogy-Making in Artificial Intelligence","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2309.06629","title":"The Relational Bottleneck as an Inductive Bias for Efficient Abstraction","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2206.05056","title":"On Neural Architecture Inductive Biases for Relational Tasks","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24,"area":null},{"id":"2207.11240","title":"Discrete Key-Value Bottleneck","created":"2022-07-22","cited_by_count":18,"area":null},{"id":"2110.09419","title":"Compositional Attention: Disentangling Search and Retrieval","created":"2021-10-18","cited_by_count":12,"area":null},{"id":"2304.00195","title":"Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers","created":"2023-04-01","cited_by_count":12,"area":null},{"id":"2302.07350","title":"Graph schemas as abstractions for transfer learning, inference, and planning","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2508.05776","title":"Whither symbols in the era of advanced neural networks?","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2204.01437","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2402.08856","title":"Approximation of relation functions and attention mechanisms","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2405.16727","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2105.10577","title":"Modelling the development of counting with memory-augmented neural networks","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2310.09612","title":"Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations","created":"2023-10-14","cited_by_count":4,"area":null},{"id":"2502.17382","title":"Unraveling the geometry of visual relational reasoning","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2207.08012","title":"Meta-Referential Games to Learn Compositional Learning Behaviours","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2302.04238","title":"Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2310.03240","title":"Learning Hierarchical Relational Representations through Relational Convolutions","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2406.01012","title":"Attention-based Iterative Decomposition for Tensor Product Representation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2411.08290","title":"RESOLVE: Relational Reasoning with Symbolic and Object-Level Features Using Vector Symbolic Processing","created":"2024-11-13","cited_by_count":2,"area":null},{"id":"2503.09781","title":"Learning richness modulates equality reasoning in neural networks","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2402.18426","title":"A Relational Inductive Bias for Dimensional Abstraction in Neural Networks","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2210.12739","title":"Functional Indirection Neural Estimator for Better Out-of-distribution Generalization","created":"2022-10-23","cited_by_count":0,"area":null},{"id":"2404.11870","title":"Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2406.06976","title":"Discrete Dictionary-based Decomposition Layer for Structured Representation Learning","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2503.23212","title":"Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2609.20530","title":"Relational Attention for Data-Efficient Language Modeling","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.24942","title":"Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}