AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Implicit Neural Representation Facilitates Unified Universal Vision Encoding

Matthew Gwilliam, Xiao Wang, Xuefeng Hu, Zhenheng Yang

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 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
make INR hyper-network patch-wise (ablation)TransINR hyper-network · ImageNette reconstructionPSNR: 27.15 -> 51.96Improved
add global token (ablation)HUVR hyper-network · ImageNette reconstructionPSNR: 51.96 -> 53.36Improved
add TinTok compression (ablation)HUVR hyper-network · ImageNette reconstructionPSNR: 53.36 -> 48.58Hurt
distill from DINOv3 to global token only vs none (ablation)HUVR ViT-B · ImageNet linear probe d=768accuracy: 11.4 -> 82.9Improved
distill to patch tokens (ablation)HUVR ViT-B · ADE20KmIoU: 4.18 -> 45.23Improved
distill to both global and patch tokens (ablation)HUVR ViT-B · ImageNet reconstructionPSNR: 28.42 -> 25.33Hurt
add INR reconstruction objective (ablation)HUVR ViT-B · ImageNet TinToks d=32accuracy: 64.2 -> 68.2Improved
remove attention from TinTok decoder (ablation)HUVR ViT-B · TinToks classification vs reconstructionaccuracy: 69.7 -> 73.5 acc; PSNR 25.35 -> 24.90Mixed
double INR hidden dim to 512 (ablation)HUVR ViT-B · ADE20KmIoU: 43.85 -> 23.36Hurt
use larger distillation teacher (ViT-L vs ViT-B) (ablation)HUVR ViT-B · ImageNet linear probeaccuracy: 82.5 -> 80.3 at 10 ep; 84.1 -> 84.6 at 50 epMixed
use HUVR instead of DINOv3 for ViT-BViT-B/16 · ImageNet linear probeaccuracy: 84.6 -> 85.0Improved
use HUVR TinToks instead of DINOv3 PCA at 32 dimsViT-B · ImageNet-1k linear probeaccuracy: 64.1 -> 79.4Improved

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