AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels

Vijay Veerabadran, Srinivas Ravishankar, Yuan Tang, Ritik Raina, Virginia R. de Sa

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures · 1 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
replace stability-based halting with learned ACT halting (ablation)hConvGRU · PathFinder-21accuracy (%): 50.0 -> 82.63Improved
replace stability-based halting with learned ACT halting (LocRNN) (ablation)hConvGRU · PathFinder-24accuracy (%): 50.0 -> 85.81Improved
replace stability-based halting with LocRNN ACT (ablation)hConvGRU · Mazes-19% mazes solved: 50.26 ± 6.04 -> 86.83 ± 2.94Improved
replace stability-based halting with LocRNN ACT (ablation)hConvGRU · Mazes-25% mazes solved: 21.36 ± 2.82 -> 49.99 ± 4.48Improved
replace fixed-iteration hConvGRU with LocRNN (ACT)hConvGRU · PathFinder-21accuracy (%): 64.21 -> 92.89 ± 0.9Improved
replace ConvGRU with LocRNN (interneuron population)ConvGRU (ACT) · PathFinder-Mixedaccuracy (%): 95.26 -> 97.13Improved
replace ConvGRU with LocRNNConvGRU (ACT) · PathFinder-24accuracy (%): 74.14 ± 6.52 -> 85.81 ± 5.57Improved
replace ConvGRU with LocRNNConvGRU (ACT) · Mazes-Mixed% mazes solved: 98.4 -> 98.4No clear effect
replace ConvGRU with LocRNNConvGRU (ACT) · Mazes-25% mazes solved: 46.93 ± 4.2 -> 49.99 ± 4.48No clear effect
use weight-tied residual network instead of gated recurrent cellsR-ResNet-30 (ACT) · PathFinder-Mixedaccuracy (%): 95.26 -> 49.37Hurt
use weight-tied residual network instead of gated recurrent cellsR-ResNet-30 (ACT) · Mazes-Mixed% mazes solved: 98.4 -> 0.0Hurt
add ACT halting to ConvGRU and extrapolate with more iterations vs fixed iterationsConvGRU · Mazes-19% mazes solved: 16.2 ± 2.66 -> 75.1 ± 11.96Improved

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