AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction

Sinan Du, Jiahao Guo, Bo Li, Shuhao Cui, Zhengzhuo Xu, Yifu Luo, Yongxian Wei, Kun Gai, Xinggang Wang, Kai Wu, Chun Yuan

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 11 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
raise codebook dimension from 384 to 1536 (ablation)VQRAE codebook · ImageNet-1K (stage 1 ablation, 20 epochs)rFID: 7.69 -> 2.65Improved
raise codebook dimension from 384 to 1536 (ablation)VQRAE codebook · ImageNet-1K (stage 1 ablation, 20 epochs)codebook utilization: 64% -> 100%Improved
raise codebook dimension from 1536 to 1920 (ablation)VQRAE codebook · ImageNet-1K (stage 1 ablation, 20 epochs)rFID: 2.65 -> 2.69No clear effect
use codebook dimension at most 256 (ablation)VQRAE codebook · ImageNet-1K (stage 1 ablation, 20 epochs)reconstruction: NAHurt
increase codebook size from 4096 to 16384 (ablation)VQRAE codebook · ImageNet-1K (stage 1 ablation, 20 epochs)rFID: 7.07 -> 2.65Improved
increase codebook size from 16384 to 32768 (ablation)VQRAE codebook · ImageNet-1K (stage 1 ablation, 20 epochs)rFID: 2.65 -> 2.78Hurt
add second-stage encoder finetuning with self-distillation (ablation)VQRAE · ImageNet-1K val reconstruction (training strategy ablation)rFID: 2.84 -> 2.71No clear effect
add self-distillation to end-to-end training (ablation)VQRAE · MME-P (training strategy ablation)MME-P: 608.9 -> 1435.2Improved
add two-stage training on top of self-distillation (ablation)VQRAE · MME-P (training strategy ablation)MME-P: 1435.2 -> 1439.1Improved
add self-distillation to end-to-end training (ablation)VQRAE · ImageNet-1K val reconstructionPSNR: 21.35 -> 19.68Hurt
add self-distillation to end-to-end training (ablation)VQRAE · TextVQA (training strategy ablation)accuracy: 7.0 -> 42.6Improved
add two-stage training on top of self-distillation (ablation)VQRAE · TextVQA (training strategy ablation)accuracy: 42.6 -> 44.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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