AI News HubLIVE
原文2 min read

AI Engram: In Search of Memory Traces in Artificial Intelligence

A new geometric framework identifies 'AI engrams'—identifiable memory traces in deep neural networks—by formalizing neuroscientific criteria into a constrained inverse problem. The closed-form estimator isolates individual memories from entangled parameters, enabling surgical composition or erasure via linear arithmetic without iterative optimization. Experiments from MLPs to LLMs demonstrate causal validity and scalability, bridging biological memory and representation learning.

SourcearXiv AIAuthor: Jea Kwon, Dong-Kyum Kim, Jiwon Kim, Yonghyun Kim, Woong Kook, Meeyoung Cha

[2606.14997] AI Engram: In Search of Memory Traces in Artificial Intelligence

[Submitted on 12 Jun 2026]

Title:AI Engram: In Search of Memory Traces in Artificial Intelligence

View a PDF of the paper titled AI Engram: In Search of Memory Traces in Artificial Intelligence, by Jea Kwon and 5 other authors

View PDF HTML (experimental)

Abstract:Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces analogous to biological memory units remains an open question. This work introduces a geometric framework to identify such "AI engrams" by formalizing the neuroscientific criteria of specificity, reactivation, sufficiency, and necessity into a constrained inverse problem. We derive a closed-form estimator that isolates individual memory traces from globally entangled parameters, and show that this biologically-derived solution corresponds to a natural gradient update on the parameter manifold. AI engrams enable surgical manipulation of learned knowledge: any subset of memories can be composed or erased through linear arithmetic, without iterative optimization. Experiments ranging from simple MLPs to LLMs demonstrate the causal validity and substantial scalability of AI engrams. Together, these results bridge theories of biological memory and artificial representation learning and offer geometric insight into how deep networks simultaneously support functional specificity within distributed storage.

Comments: Accepted to ICML 2026 (Oral). Code is available at this https URL

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2606.14997 [cs.AI]

(or arXiv:2606.14997v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.14997

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jea Kwon [view email] [v1] Fri, 12 Jun 2026 22:36:52 UTC (12,079 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled AI Engram: In Search of Memory Traces in Artificial Intelligence, by Jea Kwon and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)