{"total":21,"rows":[{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"area":null},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44,"area":null},{"id":"2109.02157","title":"Learning with Holographic Reduced Representations","created":"2021-09-05","cited_by_count":25,"area":null},{"id":"2305.19534","title":"Recasting Self-Attention with Holographic Reduced Representations","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2106.01317","title":"Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization","created":"2021-06-02","cited_by_count":11,"area":null},{"id":"2403.05330","title":"Consecutive Batch Model Editing with HooK Layers","created":"2024-03-08","cited_by_count":10,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2103.01521","title":"On the Memory Mechanism of Tensor-Power Recurrent Models","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2208.06061","title":"Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2306.00751","title":"Differentiable Tree Operations Promote Compositional Generalization","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2202.02363","title":"Meta-Reinforcement Learning with Self-Modifying Networks","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2212.14374","title":"Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks","created":"2022-12-29","cited_by_count":4,"area":null},{"id":"2312.15310","title":"Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations","created":"2023-12-23","cited_by_count":4,"area":null},{"id":"2410.22669","title":"A Walsh Hadamard Derived Linear Vector Symbolic Architecture","created":"2024-10-30","cited_by_count":4,"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":"2211.09440","title":"Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks","created":"2022-11-17","cited_by_count":1,"area":null},{"id":"2103.12686","title":"PAC-learning gains of Turing machines over circuits and neural networks","created":"2021-03-23","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":"2509.24732","title":"Who invented deep residual learning?","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2609.36529","title":"Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}