Self-Transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
- 10 September 2026
- book chapter
- Published by Springer Nature
- p. 417-434
Abstract
No abstract availableKeywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models2025
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers2024
- SD-DiT: Unleashing the Power of Self-Supervised Discrimination in Diffusion Transformer*2024
- Exploiting Diffusion Prior for Generalizable Dense Prediction2024
- Scalable Diffusion Models with Transformers2023
- Masked Diffusion Transformer is a Strong Image Synthesizer2023
- Your Diffusion Model is Secretly a Zero-Shot Classifier2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- On the Efficacy of Knowledge Distillation2019
- Principal component analysisWIREs Computational Statistics, 2010