AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Coupling Liquid Time-Constant Encoders with Modern Hopfield Memory

Bishal Ranjan Swain, Kyung Joo Cheoi, Jaepil Ko

CVPR 2026 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures

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
couple Hopfield memory retrieval to LTC (ablation)LTC · ablation avg over datasetsaccuracy: 87.99 -> 90.42Improved
match LTC parameter count without memory (ablation)LTC · ablation avg over datasetsaccuracy: 87.99 -> 88.47No clear effect
freeze Hopfield weights at initialization (ablation)LTC-MHN · ablation avg over datasetsaccuracy: 90.42 -> 88.03Hurt
set beta to 0 (uniform retrieval) (ablation)LTC-MHN · ablation avg over datasetsaccuracy: 90.42 -> 82.21Hurt
shuffle memory indices each epoch (ablation)LTC-MHN · ablation avg over datasetsaccuracy: 90.42 -> 80.26Hurt
add Hopfield memory to LTC (ablation)LTC · ablation avg over datasetsHessian trace: 1.6x10^-2 -> 1.55x10^-3Improved
add Hopfield memory to LTCLTC · Gestureaccuracy: 68.45% -> 71.23%Improved
add Hopfield memory to LTCLTC · Sequential MNISTaccuracy: 95.36% -> 97.30%Improved
add Hopfield memory to LTCLTC · OzoneF1-score: 0.304 -> 0.321Improved
add Hopfield memory to LTCLTC · Powersquared-error: 0.592 -> 0.629Hurt

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