AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity

Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, Anqi Wu

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Low-rank and diffusion neural dynamics · 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
add group-wise independence (partial correlation penalty) to the low-rank RNNlrRNN · Synthetic Lorenz+Thomas latentslatent partial correlation: 0.86 -> 0.13Improved
train factorization end-to-end instead of post-hoc ICA on lrRNN latents (ablation)FacRNN · Synthetic datalatent factorizationImproved
add factorization to low-rank RNNlrRNN/LINT · Synthetic datareconstruction R2: approximately 0.85 for all methodsNo clear effect
add factorization with two rank-1 groupslrRNN · Monkey M1 (K=2)alignment R2: 0.5 -> 0.65Improved
use two rank-2 groups at K=4 (ablation)FacRNN · Monkey M1 (K=4)alignment R2: about 0.8Improved
use 4 rank-1 groups (full independence) instead of 2 rank-2 groups (ablation)FacRNN · Monkey M1 (K=4)alignment R2Hurt
replace linear encoder/decoder with MLP (ablation)FacRNN · Monkey M1 (K=2)alignment R2No clear effect
use sophisticated SMC inference without direction labels (ablation)lrRNN · Monkey M1 (K=4)alignment R2Hurt
increase total latent components K up to six (ablation)FacRNN (G=K, H=1) · Mouse voltage imagingreconstruction R2Improved
vary number of groups G at fixed K=12 (ablation)FacRNN · Mouse voltage imagingreconstruction R2No clear effect
use 6 rank-2 groups instead of 6 rank-1 groups (ablation)FacRNN · Mouse voltage imagingbetween-group total correlation: 0.159 -> 0.110Improved

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