A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning

Computer Science > Computer Vision and Pattern Recognition [Submitted on 25 Mar 2026] A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning Changyu Liu, James Chenhao Liang, Wenhao Yang, Yiming Cui, Jinghao Yang, Tianyang Wang, Qifan Wang, Dongfang Liu, Cheng Han Diffusion models have significantly reshaped the field of generative artificial intelligence and are now increasingly explored for their capacity in discriminative representation learning. Diffusion Transformer (DiT) has recently gained attention as a promising alternative to conventional U-Net-based diffusion models, demonstrating a promising avenue for downstream discriminative tasks via generative pre-training. However, its current training efficiency and representational capacity remain largely constrained due to the inadequate timestep searching and insufficient exploitation of DiT-specific feature representations. In light of this view, we introduce Automatically Selected Timestep (A-SelecT) that dynamically pinpoints DiT's most information-rich timestep from the selected transformer feature in a single run, eliminating the need for both computationally intensive exhaustive timestep searching and suboptimal discriminative feature selection. Extensive experiments on classification and segmentation benchmarks demonstrate that DiT, empowered by A-SelecT, surpasses all prior diffusion-based attempts efficiently and effectively. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Image and Video Processing (eess.IV) Cite as: arXiv:2603.25758 [cs.CV]   (or arXiv:2603.25758v1 [cs.CV] for this version)   https://doi.org/10.48550/arXiv.2603.25758 Focus to learn more Submission history From: Changyu Liu [view email] [v1] Wed, 25 Mar 2026 19:17:14 UTC (40,866 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CV < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI cs.LG eess eess.IV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)