AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Exploring State-Space Models for Data-Specific Neural Representations

Jinsung Lee, Suha Kwak

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Neuro-symbolic probabilistic layers

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 Mamba/ConvNeXt with S3K convolution in LPNetLPNet · KodakPSNR: 25.99 -> 28.09 (vs ConvNeXt); 27.44 -> 28.09 (vs LPNet-Conv)Improved
use S3K instead of Mamba in LPNet (ablation)LPNet · ObjaversePSNR: 17.74 -> 18.34Improved
use LPNet layout instead of ConvNeXt with convolution (ablation)ConvNeXt encoder · KodakPSNR: 25.99 -> 27.44Improved
use Laplacian pyramid encoder instead of stacked SSM/conv (ablation)Mamba encoder · CIFAR-100 reconstructionPSNR: 24.82 -> 26.58Improved
stack SSM and conv layers instead of single SSM block (ablation)S5 encoder · CIFAR-100 reconstructionPSNR: 25.76 -> 24.84Hurt
apply SSMs on image pyramid vs single block (ablation)Mamba encoder · CIFAR-100 reconstructionPSNR: 24.90 -> 24.78Hurt
replace Transformer with SSM block (baseline architecture) (ablation)S4ND encoder · CIFAR-100 reconstructionPSNR: 24.75 -> 26.00Improved
add subsequent 1x1 convolution (ablation)S3K · Bunny (HNeRV decoder)PSNR: 36.37 -> 36.67Improved
add adaptive B (ablation)S3K with 1x1 conv · Bunny (HNeRV decoder)PSNR: 36.67 -> 36.92Improved
add adaptive Delta (without inverted bottleneck) (ablation)S3K with adaptive B · Bunny (HNeRV decoder)PSNR: 36.92 -> 36.26Hurt
add SiLU and RMSNorm (ablation)S3K with inverted bottleneck · Bunny (HNeRV decoder)PSNR: 36.94 -> 37.03Improved
replace convolutional NeRV encoder with LPNet-S3K encoder (SNeRV decoder)SNeRV · UVGPSNR: 33.28 -> 33.66Improved

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