Paper Detail

Engram Neuron Inspired Adaptive Memorization for Lifelong Learning

Suiyang Jiang, Bomin Wang, Hangqi Zhou, Jianfeng Feng, Xiahai Zhuang

arxiv Score 14.0

Published 2026-10-10 · First seen 2026-10-14

Research Track A · General AI

Abstract

Lifelong learning enables artificial systems to adapt to changing environments. To achieve this, an effective artificial learner should dynamically reorganize past and new experiences, maintaining stability while enabling flexible knowledge integration. However, existing efforts primarily mitigate catastrophic forgetting, lacking the ability to adaptively update memory akin to biological systems. Here, by integrating the full memory life cycle of engram neurons into artificial learners, we propose a framework that constructs a structured memory from gradient representations, which regulates parameter updates and guides memory management. Through comprehensive evaluations on four benchmarks, our approach shows promising lifelong learning capability, maintaining stability over long task sequences and supporting flexible adaptation. Beyond the performance gains, our approach offers a computational perspective on robust and flexible lifelong learning, echoing mechanisms observed in biological memory systems.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{jiang2026engram,
  title = {Engram Neuron Inspired Adaptive Memorization for Lifelong Learning},
  author = {Suiyang Jiang and Bomin Wang and Hangqi Zhou and Jianfeng Feng and Xiahai Zhuang},
  year = {2026},
  abstract = {Lifelong learning enables artificial systems to adapt to changing environments. To achieve this, an effective artificial learner should dynamically reorganize past and new experiences, maintaining stability while enabling flexible knowledge integration. However, existing efforts primarily mitigate catastrophic forgetting, lacking the ability to adaptively update memory akin to biological systems. Here, by integrating the full memory life cycle of engram neurons into artificial learners, we propo},
  url = {https://arxiv.org/abs/2610.14940},
  keywords = {cs.CV},
  eprint = {2610.14940},
  archiveprefix = {arXiv},
}

Metadata

{}