"training-free acceleration" Papers
6 papers found
Accelerating Diffusion Sampling via Exploiting Local Transition Coherence
shangwen zhu, Han Zhang, Zhantao Yang et al.
ICCV 2025posterarXiv:2503.09675
BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
Hui Zhang, Tingwei Gao, Jie Shao et al.
CVPR 2025posterarXiv:2503.15927
11
citations
EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
Yantai Yang, Yuhao Wang, Zichen Wen et al.
NeurIPS 2025oralarXiv:2506.10100
31
citations
Grouped Speculative Decoding for Autoregressive Image Generation
Junhyuk So, Juncheol Shin, Hyunho Kook et al.
ICCV 2025posterarXiv:2508.07747
3
citations
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
Bowei Guo, Shengkun Tang, Cong Zeng et al.
ICCV 2025posterarXiv:2510.11962
1
citations
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
Huanpeng Chu, Wei Wu, Guanyu Feng et al.
ICCV 2025posterarXiv:2508.16212
6
citations