arXiv Artificial Intelligence

MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge

1 hour ago 07.10.2026 07:00 👁 1 views
MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge

Quick summary

arXiv:2610.08669v1 Announce Type: cross Abstract: On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass. This paper introduces Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around

Key takeaways

  • arXiv:2610.08669v1 Announce Type: cross Abstract: On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment.
  • Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass.
  • This paper introduces Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around

Why it matters

The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗