AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?

Lingchen Sun, Rongyuan Wu, zhengqiang ZHANG, Ruibin LI, Yujing Sun, Shuaizheng LIU, Lei Zhang

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 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
add VAE structure guidance (ablation)SiT-B/2 · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 38.60 -> 32.20Improved
add self-guided representation (ablation)SiT-B/2 · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 38.60 -> 25.21Improved
add self-guided representation on top of VAE structure guidance (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 32.20 -> 22.91Improved
add VAE structure guidance to the guiding model (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 25.21 -> 22.91Improved
use two-stage instead of one-stage training (ablation)Self-Transcendence · ImageNet 256 no CFG (SiT-B/2)FID: 34.50 -> 20.49Improved
use VAE-aligned guiding model instead of REPA-trained teacher (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 23.40 -> 22.91Improved
raise guidance scale from 1.0 to 30.0 (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 29.30 -> 22.91Improved
raise guidance scale from 30.0 to 60.0 (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 22.91 -> 23.57Hurt
train guiding model 300K instead of 200K iterations (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 22.91 -> 23.05No clear effect
train guiding model 200K instead of 50K iterations (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 28.32 -> 22.91Improved
guide layer 6 from layer 8 instead of the same layer 6 (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 24.37 -> 22.91Improved
guidance weight 0.5 instead of 0.1 (ablation)Self-Transcendence · ImageNet 256 ablation (SiT-B/2, 80 ep)FID: 24.28 -> 22.91Improved

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