AI Paper Atlas

Research map / Architectures and efficiency / Quantization

VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers

Xianghong Fang, Yuan Yuan, Dehan Kong, Tim G. J. Rudner

ICLR 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 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 decoder adaptation (5 epochs) after VQ substitution (ablation)MMD VAR (K=4096) · ImageNet-1Kr-FID: 1.52 -> 0.91Improved
add decoder adaptation (5 epochs) (ablation)MMD VAR (K=8192) · ImageNet-1Kr-FID: 1.49 -> 0.81Improved
add decoder adaptation (ablation)Vanilla VQ fixed-scale (K=16384) · ImageNet-1Kr-FID: 10.61 -> 5.02Improved
add decoder adaptation (ablation)EMA VQ fixed-scale (K=16384) · ImageNet-1Kr-FID: 1.86 -> 1.11Improved
extend decoder adaptation from 5 to 20 epochs (ablation)MMD VAR · ImageNet-1Kr-FID: 0.91 -> 0.79 (K=4096); 0.81 -> 0.74 (K=8192)Improved
replace native VQ with distribution-aligned VQ (MMD) vs Vanilla VQ (ablation)VQ-Transplant · ImageNet-1K substitution (K=4096)codebook utilization: 38.2% -> 100%Improved
use MMD VQ instead of Wasserstein VQ (ablation)VQ-Transplant · ImageNet-1K adaptation (K=4096)r-FID: 0.93 -> 0.91No clear effect
lower quantization error alone (substitution without decoder adaptation) (ablation)MMD VAR · ImageNet-1Kr-FID: 0.92 (original) -> 1.52 (substituted)Hurt
use VQ-Transplant instead of from-scratch training (ablation)MMD VAR · ImageNet-1Kr-FID: 1.40 -> 0.91 (K=4096)Improved
apply VQ-Transplant to LDM-16 continuous tokenizer instead of VAR (ablation)VQ-Transplant · ImageNet-1Kr-FID, r-ISHurt

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