AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

Guanjie Chen, Xinyu Zhao, Yucheng Zhou, Xiaoye Qu, Tianlong Chen, Yu Cheng

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 9 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 long skip connections to DiT-XL and trainDiT-XL · ImageNet 256 class-to-image (cfg=1.0)FID: 9.49 -> 8.37Improved
add long skip connections to LatteLatte · UCF101 class-to-videoFVD: 155.22 -> 141.30Improved
add long skip connections to Latte (text-to-video continual training)Latte · VBench text-to-video (Latte, 50-step DDIM)VBench score (%): 76.14 -> 75.60No clear effect
cache at timesteps 700->50 instead of 950->300 (ablation)Skip-DiT · VBench text-to-video, caching timestep ablation (Skip-DiT)PSNR: 20.58 -> 29.52Improved
cache at timesteps 700->50 instead of 950->300 (ablation)Skip-DiT · VBench text-to-video, caching timestep ablation (Skip-DiT)VBench score (%): 75.48 -> 75.51No clear effect
cache at 700->50 instead of 900->50 (ablation)Skip-DiT · VBench text-to-video, caching timestep ablation (Skip-DiT)PSNR: 22.13 -> 29.52Improved
cache block 27 linked via LSC 0 rather than LSC 2 (ablation)Skip-DiT · Connection selection for caching (Latte T2V)Similarity (%): 99.66 -> 99.88Improved
integrate PAB caching with Skip-DiT instead of Latte (ablation)PAB235 · Compatibility with caching methodsVBench drop: 2.37 -> 1.81Improved
integrate PAB caching with Skip-DiT instead of Latte (ablation)PAB469 · Compatibility with caching methodsVBench drop: 5.94 -> 3.96Improved
use Skip-DiT instead of Latte at 10 sampling stepsLatte · Few-step text-to-video (10 steps)Delta VBench (%): 1.73 -> 0.94Improved
use Skip-DiT instead of Latte at 5 sampling stepsLatte · Few-step text-to-video (5 steps)SSIM: 0.53 -> 0.50Hurt
increase cache interval n from 2 to 6 (ablation)Skip-DiT · UCF101 class-to-video (Latte)FVD: 141.42 -> 151.77Hurt

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