AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba

Donghyun Lee, Yuhang Li, Ruokai Yin, Shiting Xiao, Priyadarshini Panda

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LIM neurons and membrane transfer on top of LoRA (ablation)Memba · Commonsense reasoning (Mamba 130M)accuracy: 43.8 -> 44.3Improved
add LIM neurons and membrane transfer on top of LoRA (ablation)Memba · VTAB-1k Specialized (Vim-S)accuracy: 85.3 -> 85.7Improved
add cross-layer membrane transfer to LIM + LoRA (ablation)Memba · Commonsense reasoning (Mamba 130M)accuracy: 44.0 -> 44.3Improved
add LoRA to LIM + membrane transfer (ablation)Memba · VTAB-1k Specialized (Vim-S)accuracy: 84.0 -> 85.7Improved
apply LoRA to both in_proj and out_proj instead of one (ablation)Memba · Commonsense reasoning (Mamba 790M)accuracy: 52.1 -> 52.3Improved
apply both in_proj and out_proj LoRA instead of in_proj only (ablation)Memba · VTAB-1k (Vanilla-VMamba-S)accuracy: 73.64 -> 73.48Hurt
exclude in_proj or out_proj from LoRA placement (ablation)Memba-130M · Commonsense reasoningaccuracy: -1.2% (in), -0.8% (out)Hurt
raise the leaky factor tau from 1/5 to 1/2 (ablation)LIM neuron · VTAB-1k Specialized (Vim-S)accuracy: 85.0 -> 85.7Improved
set threshold V_th to 1 rather than 0.5, 2 or 3 (ablation)LIM neuron · VTAB-1k Specialized (Vim-S)accuracy: 85.4 / 85.3 / 85.2 -> 85.7Improved
use Memba (in+out_proj) instead of full fine-tuningMamba 790M · Commonsense reasoningaccuracy: 51.6 -> 52.3Improved
use Memba (in+out_proj) instead of full fine-tuningVim-S · VTAB-1k (avg)accuracy: 50.08 -> 72.40Improved
use Memba (in+out_proj) instead of best prior PEFT HybridVim-S · VTAB-1k (avg)accuracy: 72.05 -> 72.40Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy