mlsanityData to 7 Oct 2026

Metalearned Neural Memory

arXiv 1907.09720 ↗First posted 23 Jul 2019cs.NE cs.LG stat.MLcited by 44

Not on the map. Why?

Abstract (arXiv)

We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading from the neural memory function amounts to pushing an input (the key vector) through the function to produce an output (the value vector). Writing to memory means changing the function; specifically, updating the parameters of the neural network to encode desired information. We leverage training and algorithmic techniques from metalearning to update the neural memory function in one shot. The proposed memory-augmented model achieves strong performance on a variety of learning problems, from supervised question answering to reinforcement learning.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 8; 2023: 4; 2024: 7; 2025: 11; 2026: 4.

44 papers.

Sort:

By area:

  1. 2021Linear Transformers Are Secretly Fast Weight Programmerscited by 471
  2. 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Lengthcited by 373
  3. 2024Titans: Learning to Memorize at Test Timecited by 303
  4. 2024Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentioncited by 194
  5. 2025Kimi Linear: An Expressive, Efficient Attention Architecturecited by 169
  6. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 146
  7. 2021Going Beyond Linear Transformers with Recurrent Fast Weight Programmerscited by 84
  8. 2024Gated Slot Attention for Efficient Linear-Time Sequence Modelingcited by 73
  9. 2025Nested Learning: The Illusion of Deep Learning Architecturescited by 69
  10. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  11. 2025It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimizationcited by 60
  12. 2025ATLAS: Learning to Optimally Memorize the Context at Test Timecited by 57
32 more
  1. 2026Attention Residualscited by 57
  2. 2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 40
  3. 2021Combining pre-trained language models and structured knowledgecited by 25
  4. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 22
  5. 2022Meta-Learning Fast Weight Language Modelscited by 20
  6. 2021Hierarchical Variational Memory for Few-shot Learning Across Domainscited by 14
  7. 2021Few-Shot Action Recognition with Compromised Metric via Optimal Transportcited by 12
  8. 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformerscited by 12
  9. 2025Comba: Improving Bilinear RNNs with Closed-loop Controlcited by 12
  10. 2026Memory Caching: RNNs with Growing Memorycited by 12
  11. 2021Meta-Learning Bidirectional Update Rulescited by 10
  12. 2022Asking for Knowledge: Training RL Agents to Query External Knowledge Using Languagecited by 10
  13. 2023Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithmcited by 9
  14. 2022Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitationcited by 8
  15. 2023Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspacecited by 7
  16. 2025TNT: Improving Chunkwise Training for Test-Time Memorizationcited by 7
  17. 2021Learning to Rehearse in Long Sequence Memorizationcited by 6
  18. 2023Metalearning Continual Learning Algorithmscited by 6
  19. 2025Fast weight programming and linear transformers: from machine learning to neurobiologycited by 6
  20. 2021Neural Sequence-to-grid Module for Learning Symbolic Rulescited by 5
  21. 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNscited by 3
  22. 2025Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environmentscited by 3
  23. 2021Meta-Learning with Variational Semantic Memory for Word Sense Disambiguationcited by 2
  24. 2024Attention-based Iterative Decomposition for Tensor Product Representationcited by 2
  25. 2021Combining Transformers with Natural Language Explanationscited by 1
  26. 2022Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networkscited by 1
  27. 2026Proteus: Incremental Memory Activation for Long-Context Sequence Modelingcited by 1
  28. 2022Functional Indirection Neural Estimator for Better Out-of-distribution Generalizationcited by 0
  29. 2024Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottleneckscited by 0
  30. 2024Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddingscited by 0
  31. 2025ResFormer: All-Time Reservoir Memory for Long Sequence Classificationcited by 0
  32. 2026Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengthscited by 0