AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers

Mengping Yang, Zhiyu Tan, Binglei Li, Xiaomeng Yang, Hesen Chen, Hao Li

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 3 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 DiverseDiT (long residuals + diversity loss)SiT-B · ImageNet 256x256 no CFG, 400KFID: 36.80 -> 28.05Improved
add DiverseDiTREPA-B · ImageNet 256x256 no CFG, 400KFID: 22.99 -> 17.29Improved
add DiverseDiTREPA-XL · ImageNet 256x256 no CFG, 400KFID: 8.73 -> 8.09Improved
add DiverseDiTMeanFlow-XL/2 (one-step) · ImageNet 256x256 one-step, no CFGFID: 5.94 -> 5.69Improved
add DiverseDiT instead of DispLossMeanFlow-XL/2 (one-step, CFG) · ImageNet 256x256 one-step with CFGFID: 3.21 -> 2.99Improved
add representation diversity loss (ablation)SiT-B + DiverseDiT · ImageNet 256x256 no CFG, 400KFID: 32.77 -> 28.05Improved
add long residual connections (ablation)SiT-B + DiverseDiT · ImageNet 256x256 no CFG, 400KFID: 33.72 -> 28.05Improved
add long residual connections (ablation)REPA-B + DiverseDiT · ImageNet 256x256 no CFG, 400KFID: 18.18 -> 17.29Improved
combine orthogonality, mutual-information and dispersion losses instead of one (ablation)REPA-B + DiverseDiT · ImageNet 256x256 no CFG, 400KFID: 18.97 -> 17.29 (vs only Lorth)Improved
use adaptive loss weight range [0.1, 0.5] instead of wider ranges (ablation)SiT-B + DiverseDiT · ImageNet 256x256 no CFG, 400KFID: 31.85 -> 28.05Improved
use constant diversity-loss weight instead of adaptive (ablation)SiT-B + DiverseDiT · ImageNet 256x256 no CFGFID: 28.05 -> divergeHurt
add DispLoss and SRA on top of DiverseDiTSiT-B · ImageNet 256x256 no CFG, 400KFID: 28.05 -> 24.98 -> 21.95Improved

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