7 papers · 1 filter
Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache
Zhirong Shen, Rui Huang, Chang Zou +10
Diffusion Transformers have become the dominant paradigm in generative AI, but their high computational costs severely hinder real-time applications. Prediction-based feature cachi…
AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation
Haoran Qin, Zhengan Yan, Shikang Zheng +9
Diffusion Transformers (DiTs) achieve high-quality generation but are costly due to iterative sampling. Dynamic-resolution sampling reduces early-stage cost by denoising at low res…
LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
Jinshan Liu, Haoran Qin, Xiaobing Tu +9
Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical d…
STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models
Qingyan Wei, Guangzhao Li, Xiaobing Tu +5
On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student. However, existing OPD metho…
EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
Zexuan Yan, Yuzhou Wu, Yue Ma +9
Egocentric video offers rich manipulation experience for embodied AI, yet collecting diverse egocentric data across scenes, objects, motions, and embodiments remains costly. We pre…
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
Zhengan Yan, Shikang Zheng, Haoran Qin +9
Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dyna…