AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Inferring brain plasticity rule under long-term stimulation with structured recurrent dynamics

Zhichao Liang, Jingzhe Lin, Xinyi Li, Guanyi Zhao, Quanying Liu

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures · 0 citations (OpenAlex)

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
train on chronologically ordered sessions instead of shuffled order (ablation)STEER · BCM syntheticW 2-norm alignment: -0.0025 -> 0.9606Improved
train on chronologically ordered sessions instead of shuffled order (ablation)STEER · BCM syntheticexplained variance (within-session): 0.9450 -> 0.9397No clear effect
joint learning of fast and slow dynamics instead of staged learning (ablation)STEER · BCM syntheticexplained variance (within-session): 0.9310 -> 0.9397Improved
joint learning instead of staged learning (ablation)STEER · BCM syntheticcorrelation between c and c_pred: 0.9866 -> 0.9934Improved
joint learning instead of staged learning (ablation)STEER · BCM syntheticW 2-norm alignment: 0.9602 -> 0.9606No clear effect
low-rank STEER versus MD-SSM in within-session predictionSTEER · BCM syntheticexplained variance: EV > 0.9 for all modelsNo clear effect
use rank-3 low-rank structure (ablation)STEER · Lorenzrank selection: rank 3 approximates accuratelyImproved

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