Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
- 1 October 2026
- book chapter
- Published by Springer Nature
- p. 222-239
Abstract
No abstract availableKeywords
All Related Versions
This publication has 31 references indexed in Scilit:
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic ModelsMachine Intelligence Research, 2025
- KFF: K-feature fusion token merging for vision transformerExpert Systems with Applications, 2025
- PIXART-$\Sigma $: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation2024
- BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion2024
- SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning2022
- Adaptive Token Sampling for Efficient Vision Transformers2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- A-ViT: Adaptive Tokens for Efficient Vision Transformer2022
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015