7 papers
RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
Wangbo Zhao, Yizeng Han, Zhiwei Tang +7
Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse att…
Info-Coevolution: An Efficient Framework for Data Model Coevolution
Ziheng Qin, Hailun Xu, Wei Chee Yew +6
Machine learning relies heavily on data, yet the continuous growth of real-world data poses challenges for efficient dataset construction and training. A fundamental yet unsolved q…
Dynamic Vision Mamba
Mengxuan Wu, Zekai Li, Zhiyuan Liang +9
Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists…
DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
Wangbo Zhao, Yizeng Han, Jiasheng Tang +6
Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investig…
Enhance-A-Video: Better Generated Video for Free
Yang Luo, Xuanlei Zhao, Mengzhao Chen +5
DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free ap…
Recurrent Diffusion for Large-Scale Parameter Generation
Kai Wang, Dongwen Tang, Wangbo Zhao +3
Parameter generation has long struggled to match the scale of today large vision and language models, curbing its broader utility. In this paper, we introduce Recurrent Diffusion f…