pith. sign in

arxiv: 2606.11245 · v1 · pith:VQU3ZELFnew · submitted 2026-06-05 · 💻 cs.AI · cs.NE· q-bio.NC

Position: Hippocampal Explicit Memory Is the Cornerstone for AGI

Sangjun Park This is my paper

Pith reviewed 2026-06-27 21:43 UTC · model grok-4.3

classification 💻 cs.AI cs.NEq-bio.NC
keywords explicit memoryhippocampusAGIlarge language modelsimplicit memorystrategic planningmetacognitionsymbolic reasoning
0
0 comments X

The pith

Integrating explicit memory modeled on the hippocampus is required for LLMs to achieve AGI.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that LLMs operate through a form of learning that closely matches human implicit memory, which handles pattern recognition and statistical associations but cannot generate the higher functions needed for general intelligence. Those functions, such as long-term planning, self-monitoring of thought, and rule-based reasoning, depend instead on explicit memory systems that store and retrieve specific facts and episodes. A sympathetic reader would therefore conclude that simply scaling current models will not close the gap and that a distinct memory architecture must be added. The position draws on neuroscience distinctions between memory types to outline what artificial explicit memory would need to accomplish.

Core claim

Higher-order cognitive functions necessary for AGI, such as long-term strategic planning, metacognition, and symbolic reasoning, heavily rely on hippocampal explicit memory and cannot arise solely from implicit statistical learning; therefore integrating explicit memory is the cornerstone for advancing LLMs toward AGI.

What carries the argument

Hippocampal explicit memory, the system that stores and retrieves specific facts and episodes to support planning, self-reflection, and symbolic operations that implicit memory cannot perform.

Load-bearing premise

Higher cognitive functions required for AGI cannot emerge from implicit statistical learning alone.

What would settle it

An LLM that reaches robust long-term planning, metacognition, and symbolic reasoning at human-comparable levels through scaling of implicit learning without any added explicit memory store.

Figures

Figures reproduced from arXiv: 2606.11245 by Sangjun Park.

Figure 1
Figure 1. Figure 1: Comparison of three memory and learning paradigms. (1) Human implicit memory forms through repeated practice and produces automatic, spontaneous responses (e.g., predicting the next note in a rehearsed melody). (2) Human explicit memory supports conscious, knowledge-based problem solving: 17 × 6 is decomposed via number concepts, the definition of multiplication, and arithmetic facts to explicitly compute … view at source ↗
Figure 2
Figure 2. Figure 2: Illustrative examples demonstrating the absence of explicit memory in ChatGPT-5, with bold text added for emphasis. (A) The first case illustrates the model’s susceptibility to the priming effect, a characteristic of implicit memory. While the model initially correctly answers that the sun rises in the east, the mere introduction of a context regarding an “Earth rotation reversal” hypothesis causes the mod… view at source ↗
Figure 3
Figure 3. Figure 3: Examples highlighting the limitations of LLMs in tasks requiring semantic memory and executive function. (A) This panel illustrates a failure in semantic memory involving basic logic. The task requires summing a sequence of ‘1’s (totaling 108), a problem solvable by a human child in minutes. However, the model incorrectly calculates the sum as 120. This failure suggests that LLMs process basic logical oper… view at source ↗
read the original abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI). This position paper argues that integrating explicit memory is the cornerstone for advancing LLMs toward AGI. The key reason is that the underlying learning mechanism of LLMs is highly analogous to human implicit memory. However, higher-order cognitive functions necessary for AGI, such as long-term strategic planning, metacognition, and symbolic reasoning, heavily rely on hippocampal explicit memory and cannot arise solely from implicit statistical learning. Drawing on findings from neuroscience, I advance this perspective and complement it with computational requirements for artificial explicit memory systems, hoping to foster further research and lay the groundwork for explicit memory integration.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. This position paper claims that LLMs operate via a learning mechanism analogous to human implicit memory, and that integrating explicit memory (modeled on hippocampal function) is the cornerstone for achieving AGI. It argues that higher-order functions required for AGI—long-term strategic planning, metacognition, and symbolic reasoning—cannot emerge from implicit statistical learning alone and draws on neuroscience to motivate computational requirements for artificial explicit memory systems.

Significance. If the central analogy and necessity claim hold, the paper would supply a concrete research direction for hybrid architectures that augment statistical learners with structured memory, potentially addressing current LLM limitations in planning and reasoning. As a perspective without new derivations, data, or falsifiable tests, its value is in framing an interdisciplinary hypothesis rather than establishing a result.

major comments (2)
  1. [Abstract] Abstract, paragraph 2: The assertion that higher-order functions 'cannot arise solely from implicit statistical learning' is load-bearing for the position yet is advanced without a computational argument, impossibility proof, or citation to results demonstrating that scaled implicit mechanisms are provably insufficient for the listed capabilities.
  2. [Abstract] Abstract and introduction: The mapping of LLM training to implicit memory is presented by definition, after which the necessity of explicit memory follows; no independent computational demonstration is supplied showing why the target AGI functions are unreachable by implicit mechanisms alone (cf. the circularity concern in the reader's note).
minor comments (1)
  1. The manuscript would benefit from an explicit section contrasting the proposed explicit-memory requirements against existing memory-augmented LLM architectures (e.g., retrieval-augmented generation) to clarify novelty.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and thoughtful report. Below we address the major comments point by point, maintaining the scope of this work as a position paper that advances a neuroscience-motivated hypothesis rather than a formal technical result.

read point-by-point responses

  1. Referee: [Abstract] Abstract, paragraph 2: The assertion that higher-order functions 'cannot arise solely from implicit statistical learning' is load-bearing for the position yet is advanced without a computational argument, impossibility proof, or citation to results demonstrating that scaled implicit mechanisms are provably insufficient for the listed capabilities.

    Authors: As a position paper our central claim is presented as a hypothesis grounded in existing neuroscience rather than a new computational proof. The manuscript cites multiple studies on hippocampal amnesia patients who retain implicit statistical learning yet show profound deficits in long-term planning, metacognition, and flexible reasoning. These empirical results from cognitive neuroscience supply the evidential basis for the necessity claim. We agree that this does not constitute a formal impossibility result for arbitrarily scaled implicit systems; the paper instead uses the biological dissociation to motivate hybrid architectures. No change is required because the current framing accurately reflects the paper's intent and cited literature. revision: no

  2. Referee: [Abstract] Abstract and introduction: The mapping of LLM training to implicit memory is presented by definition, after which the necessity of explicit memory follows; no independent computational demonstration is supplied showing why the target AGI functions are unreachable by implicit mechanisms alone (cf. the circularity concern in the reader's note).

    Authors: The analogy rests on functional parallels documented in the cognitive-science literature: LLM training performs gradual, unconscious adjustment of parameters on the basis of statistical regularities, matching the operational definition of implicit memory. The introduction already references this distinction with supporting citations before applying it to LLMs. The necessity of explicit memory then follows from the position that the cited hippocampal functions cannot be substituted by implicit mechanisms alone. We do not supply an independent computational demonstration because the paper is not a technical derivation; it is an interdisciplinary hypothesis. We see no circularity once the neuroscience grounding is recognized. revision: no

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

This position paper advances a perspective that LLMs are analogous to implicit memory and that explicit memory is required for AGI-level functions, drawing on neuroscience literature. No derivation chain, equations, fitted parameters, or self-citations are present in the provided text. The central assertion is offered as an interpretive claim rather than a result shown to reduce to its own inputs by construction. The paper is self-contained as a viewpoint and does not exhibit any of the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The paper rests on two domain assumptions drawn from neuroscience without new supporting evidence or formalization.

axioms (2)
  • domain assumption The underlying learning mechanism of LLMs is highly analogous to human implicit memory
    Stated as the key reason in the abstract.
  • domain assumption Higher-order cognitive functions necessary for AGI cannot arise solely from implicit statistical learning and require hippocampal explicit memory
    Central premise of the position (abstract).

pith-pipeline@v0.9.1-grok · 5638 in / 1300 out tokens · 33036 ms · 2026-06-27T21:43:43.946822+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

134 extracted references · 44 canonical work pages

  1. [1]

    2006 , journal =

    Declarative memory consolidation in humans: A prospective functional magnetic resonance imaging study , author =. 2006 , journal =. doi:10.1073/pnas.0507774103 , url =. https://www.pnas.org/doi/pdf/10.1073/pnas.0507774103 , abstract =

    work page doi:10.1073/pnas.0507774103 2006

  2. [2]

    2023 , journal =

    Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models , author =. 2023 , journal =

    2023

  3. [3]

    2024 , url =

    The Llama 3 Herd of Models , author =. 2024 , url =. 2407.21783 , archiveprefix =

    Pith/arXiv arXiv 2024

  4. [4]

    2007 , journal =

    Remembering the past and imagining the future: Common and distinct neural substrates during event construction and elaboration , author =. 2007 , journal =

    2007

  5. [5]

    1974 , publisher =

    Working Memory , author =. 1974 , publisher =. doi:https://doi.org/10.1016/S0079-7421(08)60452-1 , issn =

    work page doi:10.1016/s0079-7421(08)60452-1 1974

  6. [6]

    1986 , journal =

    Parallel organization of functionally segregated circuits linking basal ganglia and cortex , author =. 1986 , journal =

    1986

  7. [7]

    2025 , url =

    Qwen2.5 Technical Report , author =. 2025 , url =. 2412.15115 , archiveprefix =

    Pith/arXiv arXiv 2025

  8. [8]

    1971 , journal =

    Lamellar organization of hippocampal excitatory pathways , author =. 1971 , journal =. doi:10.1007/BF00234087 , isbn =

    work page doi:10.1007/bf00234087 1971

  9. [9]

    Psychological Review , volume =

    Acquisition of Cognitive Skill , author =. Psychological Review , volume =. 1982 , month =. doi:10.1037/0033-295X.89.4.369 , isbn =

    work page doi:10.1037/0033-295x.89.4.369 1982

  10. [10]

    Contributions of episodic retrieval and mentalizing to autobiographical thought: evidence from functional neuroimaging, resting-state connectivity, and

    Andrews-Hanna, Jessica R and Saxe, Rebecca and Yarkoni, Tal , year =. Contributions of episodic retrieval and mentalizing to autobiographical thought: evidence from functional neuroimaging, resting-state connectivity, and. Neuroimage , publisher =

  11. [11]

    2024 , month = dec, journal =

    Titans: Learning to memorize at test time , author =. 2024 , month = dec, journal =

    2024

  12. [12]

    AGI: The Cognitive Strengths and Weaknesses of Modern LLMs , author =

    Generative AI vs. AGI: The Cognitive Strengths and Weaknesses of Modern LLMs , author =. 2023 , url =. 2309.10371 , archiveprefix =

    arXiv 2023

  13. [13]

    2015 , month = aug, journal =

    Specifying the core network supporting episodic simulation and episodic memory by activation likelihood estimation , author =. 2015 , month = aug, journal =

    2015

  14. [14]

    2011 , month = nov, journal =

    The neurobiology of semantic memory , author =. 2011 , month = nov, journal =

    2011

  15. [15]

    2007 , month = feb, journal =

    The role of the basal ganglia and cerebellum in language processing , author =. 2007 , month = feb, journal =

    2007

  16. [16]

    2023 , month =

    Sparks of Artificial General Intelligence: Early experiments with GPT-4 , author =. 2023 , month =

    2023

  17. [17]

    2000 , journal =

    The cognitive and neuroanatomical correlates of multitasking , author =. 2000 , journal =

    2000

  18. [18]

    2022 , month = dec, booktitle =

    Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing , author =. 2022 , month = dec, booktitle =. doi:10.18653/v1/2022.emnlp-main.460 , url =

    work page doi:10.18653/v1/2022.emnlp-main.460 2022

  19. [19]

    2022 , month = may, journal =

    Foundational number sense training gains are predicted by hippocampal-parietal circuits , author =. 2022 , month = may, journal =

    2022

  20. [20]

    1998 , month = apr, journal =

    Classical conditioning and brain systems: the role of awareness , author =. 1998 , month = apr, journal =

    1998

  21. [21]

    2024 , journal =

    Building machines that learn and think with people , author =. 2024 , journal =. doi:10.1038/s41562-024-01991-9 , isbn =

    work page doi:10.1038/s41562-024-01991-9 2024

  22. [22]

    2020 , month = may, journal =

    How does the brain learn environmental structure? Ten core principles for understanding the neurocognitive mechanisms of statistical learning , author =. 2020 , month = may, journal =

    2020

  23. [23]

    2014 , journal =

    Performance-optimized hierarchical models predict neural responses in higher visual cortex , author =. 2014 , journal =. doi:10.1073/pnas.1403112111 , url =. https://www.pnas.org/doi/pdf/10.1073/pnas.1403112111 , abstract =

    work page doi:10.1073/pnas.1403112111 2014

  24. [24]

    2024 , month = jul, booktitle =

    Larimar: Large Language Models with Episodic Memory Control , author =. 2024 , month = jul, booktitle =

    2024

  25. [25]

    2025 , url =

    DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning , author =. 2025 , url =. 2501.12948 , archiveprefix =

    Pith/arXiv arXiv 2025

  26. [26]

    2017 , month = oct, journal =

    Episodic and semantic content of memory and imagination: A multilevel analysis , author =. 2017 , month = oct, journal =

    2017

  27. [27]

    Kumaran, D

    What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated , author =. 2016 , journal =. doi:https://doi.org/10.1016/j.tics.2016.05.004 , issn =

    work page doi:10.1016/j.tics.2016.05.004 2016

  28. [28]

    2005 , month = apr, journal =

    Reorganization and plasticity in the adult brain during learning of motor skills , author =. 2005 , month = apr, journal =

    2005

  29. [29]

    2000 , journal =

    A cortical--hippocampal system for declarative memory , author =. 2000 , journal =. doi:10.1038/35036213 , isbn =

    work page doi:10.1038/35036213 2000

  30. [30]

    2024 , month = jul, journal =

    Declarative memory supports children's math skills: A longitudinal study , author =. 2024 , month = jul, journal =

    2024

  31. [31]

    2002 , month = may, journal =

    Statistical learning of higher-order temporal structure from visual shape sequences , author =. 2002 , month = may, journal =

    2002

  32. [32]

    2002 , month = nov, journal =

    Statistical learning of new visual feature combinations by infants , author =. 2002 , month = nov, journal =

    2002

  33. [33]

    2012 , month = may, journal =

    The neural basis of metacognitive ability , author =. 2012 , month = may, journal =

    2012

  34. [34]

    2005 , journal =

    The organization of recent and remote memories , author =. 2005 , journal =. doi:10.1038/nrn1607 , isbn =

    work page doi:10.1038/nrn1607 2005

  35. [35]

    2013 , month = jan, journal =

    Mathematical logic in the human brain: semantics , author =. 2013 , month = jan, journal =

    2013

  36. [36]

    2024 , url =

    Gemma 2: Improving Open Language Models at a Practical Size , author =. 2024 , url =. 2408.00118 , archiveprefix =

    Pith/arXiv arXiv 2024

  37. [37]

    Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence,

    Large Language Models Are Not Strong Abstract Reasoners , author =. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence,. 2024 , month =. doi:10.24963/ijcai.2024/693 , url =

    work page doi:10.24963/ijcai.2024/693 2024

  38. [38]

    2011 , month = jul, journal =

    Modulation of striatal projection systems by dopamine , author =. 2011 , month = jul, journal =

    2011

  39. [39]

    Neuron , publisher =

    An Integrated Index: Engrams, Place Cells, and Hippocampal Memory , author =. Neuron , publisher =. 2020 , month =. doi:10.1016/j.neuron.2020.07.011 , isbn =

    work page doi:10.1016/j.neuron.2020.07.011 2020

  40. [40]

    Cell , publisher =

    Dynamics of Retrieval Strategies for Remote Memories , author =. Cell , publisher =. 2011 , month =. doi:10.1016/j.cell.2011.09.033 , isbn =

    work page doi:10.1016/j.cell.2011.09.033 2011

  41. [41]

    1985 , journal =

    Implicit and explicit memory for new associations in normal and amnesic subjects , author =. 1985 , journal =

    1985

  42. [42]

    2008 , month = jul, journal =

    Habits, rituals, and the evaluative brain , author =. 2008 , month = jul, journal =

    2008

  43. [43]

    2020 , month = feb, journal =

    Explicit memory and cognition in monkeys , author =. 2020 , month = feb, journal =

    2020

  44. [44]

    Neuron , address =

    Hassabis, Demis and Kumaran, Dharshan and Summerfield, Christopher and Botvinick, Matthew , year =. Neuron , address =

  45. [45]

    2007 , month = jul, journal =

    Deconstructing episodic memory with construction , author =. 2007 , month = jul, journal =

    2007

  46. [46]

    2010 , month = apr, journal =

    Switching from automatic to controlled behavior: cortico-basal ganglia mechanisms , author =. 2010 , month = apr, journal =

    2010

  47. [47]

    2019 , month = jun, journal =

    Neurobiological basis of feeling of knowing in episodic memory , author =. 2019 , month = jun, journal =

    2019

  48. [48]

    2022 , url =

    Emergent Abilities of Large Language Models , author =. 2022 , url =. 2206.07682 , archiveprefix =

    Pith/arXiv arXiv 2022

  49. [49]

    2024 , booktitle =

    Large Language Models Cannot Self-Correct Reasoning Yet , author =. 2024 , booktitle =

    2024

  50. [50]

    2007 , journal =

    Pattern Separation in the Dentate Gyrus and CA3 of the Hippocampus , author =. 2007 , journal =. doi:10.1126/science.1135801 , url =. https://www.science.org/doi/pdf/10.1126/science.1135801 , abstract =

    work page doi:10.1126/science.1135801 2007

  51. [51]

    2012 , month = mar, journal =

    Implicit and explicit olfactory memory in people with and without Down syndrome , author =. 2012 , month = mar, journal =

    2012

  52. [52]

    1993 , month = apr, journal =

    Spatial selectivity of unit activity in the hippocampal granular layer , author =. 1993 , month = apr, journal =

    1993

  53. [53]

    2025 , url =

    A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics , author =. 2025 , url =. 2310.05694 , archiveprefix =

    arXiv 2025

  54. [54]

    2002 , month = apr, journal =

    Decisions and the evolution of memory: multiple systems, multiple functions , author =. 2002 , month = apr, journal =

    2002

  55. [55]

    2010 , month = mar, journal =

    The multiplicity of self: neuropsychological evidence and its implications for the self as a construct in psychological research , author =. 2010 , month = mar, journal =

    2010

  56. [56]

    Neuron , publisher =

    Striatal Plasticity and Basal Ganglia Circuit Function , author =. Neuron , publisher =. 2008 , month =. doi:10.1016/j.neuron.2008.11.005 , isbn =

    work page doi:10.1016/j.neuron.2008.11.005 2008

  57. [57]

    2022 , month = mar, journal =

    Biological underpinnings for lifelong learning machines , author =. 2022 , month = mar, journal =. doi:10.1038/s42256-022-00452-0 , issn =

    work page doi:10.1038/s42256-022-00452-0 2022

  58. [58]

    2004 , journal =

    Memory systems of the brain: A brief history and current perspective , author =. 2004 , journal =. doi:https://doi.org/10.1016/j.nlm.2004.06.005 , issn =

    work page doi:10.1016/j.nlm.2004.06.005 2004

  59. [59]

    1996 , journal =

    Structure and function of declarative and nondeclarative memory systems , author =. 1996 , journal =. doi:10.1073/pnas.93.24.13515 , url =. https://www.pnas.org/doi/pdf/10.1073/pnas.93.24.13515 , abstract =

    work page doi:10.1073/pnas.93.24.13515 1996

  60. [60]

    2017 , journal =

    Online neural monitoring of statistical learning , author =. 2017 , journal =. doi:https://doi.org/10.1016/j.cortex.2017.02.004 , issn =

    work page doi:10.1016/j.cortex.2017.02.004 2017

  61. [61]

    1992 , month = aug, journal =

    Speech production, syntax comprehension, and cognitive deficits in Parkinson's disease , author =. 1992 , month = aug, journal =

    1992

  62. [62]

    2022 , url =

    Training language models to follow instructions with human feedback , author =. 2022 , url =. 2203.02155 , archiveprefix =

    Pith/arXiv arXiv 2022

  63. [63]

    Hosseini, Nancy Kanwisher, Joshua B

    The neural architecture of language: Integrative modeling converges on predictive processing , author =. 2021 , journal =. doi:10.1073/pnas.2105646118 , url =. https://www.pnas.org/doi/pdf/10.1073/pnas.2105646118 , abstract =

    work page doi:10.1073/pnas.2105646118 2021

  64. [64]

    2018 , journal =

    Prioritized memory access explains planning and hippocampal replay , author =. 2018 , journal =. doi:10.1038/s41593-018-0232-z , isbn =

    work page doi:10.1038/s41593-018-0232-z 2018

  65. [65]

    2010 , month = mar, journal =

    The relationship between working memory capacity and executive functioning: evidence for a common executive attention construct , author =. 2010 , month = mar, journal =

    2010

  66. [66]

    1995 , month = jul, journal =

    Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory , author =. 1995 , month = jul, journal =

    1995

  67. [67]

    2016 , booktitle =

    Memory and cognitive control circuits in mathematical cognition and learning , author =. 2016 , booktitle =

    2016

  68. [68]

    2012 , journal =

    The use of procedural knowledge in simple addition and subtraction problems , author =. 2012 , journal =. doi:https://doi.org/10.1016/j.cognition.2012.02.008 , issn =

    work page doi:10.1016/j.cognition.2012.02.008 2012

  69. [69]

    2023 , booktitle =

    Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting , author =. 2023 , booktitle =

    2023

  70. [70]

    2004 , journal =

    Computational roles for dopamine in behavioural control , author =. 2004 , journal =. doi:10.1038/nature03015 , isbn =

    work page doi:10.1038/nature03015 2004

  71. [71]

    Position: Levels of

    Morris, Meredith Ringel and Sohl-Dickstein, Jascha and Fiedel, Noah and Warkentin, Tris and Dafoe, Allan and Faust, Aleksandra and Farabet, Clement and Legg, Shane , year =. Position: Levels of. Proceedings of the 41st International Conference on Machine Learning , publisher =

  72. [72]

    2004 , journal =

    NMDA receptors, place cells and hippocampal spatial memory , author =. 2004 , journal =. doi:10.1038/nrn1385 , isbn =

    work page doi:10.1038/nrn1385 2004

  73. [73]

    Requirement for hippocampal

    Nakazawa, Kazu and Quirk, Michael C and Chitwood, Raymond A and Watanabe, Masahiko and Yeckel, Mark F and Sun, Linus D and Kato, Akira and Carr, Candice A and Johnston, Daniel and Wilson, Matthew A and Tonegawa, Susumu , year =. Requirement for hippocampal. Science , publisher =

  74. [74]

    Cohen and Larry R

    Preserved Learning and Retention of Pattern-Analyzing Skill in Amnesia: Dissociation of Knowing How and Knowing That , author =. 1980 , journal =. doi:10.1126/science.7414331 , url =. https://www.science.org/doi/pdf/10.1126/science.7414331 , abstract =

    work page doi:10.1126/science.7414331 1980

  75. [75]

    2024 , url =

    GPT-4 Technical Report , author =. 2024 , url =. 2303.08774 , archiveprefix =

    Pith/arXiv arXiv 2024

  76. [76]

    2002 , month = mar, journal =

    Learning and memory functions of the Basal Ganglia , author =. 2002 , month = mar, journal =

    2002

  77. [77]

    Proceedings of the 41st International Conference on Machine Learning , publisher =

    Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture , author =. Proceedings of the 41st International Conference on Machine Learning , publisher =. 2024 , month =

    2024

  78. [78]

    2007 , journal =

    Where do you know what you know? The representation of semantic knowledge in the human brain , author =. 2007 , journal =. doi:10.1038/nrn2277 , isbn =

    work page doi:10.1038/nrn2277 2007

  79. [79]

    2024 , journal =

    Evidence for a competitive relationship between executive functions and statistical learning , author =. 2024 , journal =. doi:10.1038/s41539-024-00243-9 , isbn =

    work page doi:10.1038/s41539-024-00243-9 2024

  80. [80]

    2023 , url =

    Holistic Evaluation of Language Models , author =. 2023 , url =. 2211.09110 , archiveprefix =

    Pith/arXiv arXiv 2023

Showing first 80 references.