AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

RecTok: Reconstruction Distillation along Rectified Flow

Qingyu Shi, Size Wu, Jinbin Bai, Kaidong Yu, Yujing Wang, Yunhai Tong, Xiangtai Li, Xuelong Li

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 4 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 flow semantic distillation (FSD) on x_t (ablation)RecTok · ImageNet 256 ablationgFID: 3.35 -> 2.27Improved
add flow semantic distillation to baseline (ablation)RecTok · ImageNet 256 ablationgFID: 12.07 -> 2.52Improved
add reconstruction distillation (RAD) after FSD (ablation)RecTok · ImageNet 256 ablationgFID: 2.52 -> 2.27Improved
add decoder finetuning (ablation)RecTok · ImageNet 256 ablationrFID: 0.65 -> 0.48Improved
add reconstruction alignment to alignment-only (ablation)RecTok · ImageNet 256 ablationgFID: 2.52 -> 2.27Improved
add alignment to reconstruction-only (ablation)RecTok · ImageNet 256 ablationgFID: 2.97 -> 2.27Improved
increase latent dimension from 16 to 128 (ablation)RecTok · ImageNet 256 ablationgFID: 2.75 -> 2.27Improved
use shift noise schedule instead of uniform (ablation)RecTok · ImageNet 256 ablationgFID: 2.50 -> 2.27Mixed
use random encoder initialization instead of VFM initialization (ablation)RecTok · ImageNet 256 ablationgFID: 2.37 -> 2.27Improved
use lightweight 1.5M transformer semantic decoder instead of 10M (ablation)RecTok · ImageNet 256 ablationgFID: 3.13 -> 2.27Improved
set semantic loss weight to 1 instead of 0.5 (ablation)RecTok · ImageNet 256 ablationgFID: 2.78 -> 2.27Improved
use two VFMs instead of one for semantic learning (ablation)RecTok · ImageNet 256 ablation (dim 128)gFID: 2.27 -> 2.51Hurt

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