AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification

Stanisław Janik, Michal Byra

ECCV 2026 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations · 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 layer-wise MoE stage before token-wise MoE (ablation)HMoE-MWT · CIFAR-10 (MoE ablation)accuracy: 62.57 -> 65.01Improved
add token-wise MoE stage after layer-wise MoE (ablation)HMoE-MWT · CIFAR-10 (MoE ablation)accuracy: 63.21 -> 65.01Improved
increase active token experts (top-2, top-4) (ablation)HMoE-MWT token-wise MoE · CIFAR-10 (MoE ablation)accuracy: 62.57 -> 62.21No clear effect
increase layer experts from 4 to 8 (ablation)HMoE-MWT · CIFAR-10 (MoE ablation)accuracy: 65.01 -> 64.03No clear effect
increase token experts from 4 to 8 (ablation)HMoE-MWT · CIFAR-10 (MoE ablation)accuracy: 65.01 -> 64.53No clear effect
add classification-loss injection (meta-learning) to HMoEHMoE · CIFAR-10 (INR classification)accuracy: 55.44 -> 65.01Improved
replace dense transformer with hierarchical MoE (no meta-learning)WT · CIFAR-10 (INR classification)accuracy: 43.78 -> 55.44Improved
increase SIREN width from 128 to 256HMoE-MWT · CIFAR-10 (INR classification)accuracy: 65.01 -> 64.40No clear effect
use HMoE instead of parameter-matched dense MWT at 11MMWT · Imagenette (parameter-matched)accuracy: 59.92 -> 62.52Improved
increase task loss weight from 0.01 to 1 (ablation)HMoE-MWT · CIFAR-10 (80/20 split ablation)accuracy: 63.14 -> 55.34Hurt
increase inner-loop steps from 1 to 6 (ablation)HMoE-MWT · CIFAR-10 (80/20 split ablation)accuracy: 57.84 -> 63.14Improved
reduce coordinate subsampling rate from 1.0 to 0.001 (ablation)HMoE-MWT · CIFAR-10 (80/20 split ablation)accuracy: 63.14 -> 11.59Hurt

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