7 papers
Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models
An Zhao, Shengyuan Zhang, Zhongjian Sun +5
Flow Matching models have demonstrated strong performance across a wide range of generative tasks. However, their reliance on ODE-based iterative sampling incurs substantial comput…
Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes
Chenye Meng, Zejian Li, Zhongni Liu +9
Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is…
Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
Zejian Li, Yize Li, Chenye Meng +7
Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typi…
Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion
Shengyuan Zhang, An Zhao, Ling Yang +7
Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the prac…
Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation
Shengyuan Zhang, Ling Yang, Zejian Li +6
Accelerating the sampling speed of diffusion models remains a significant challenge. Recent score distillation methods distill a heavy teacher model into a student generator to ach…
Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
An Zhao, Shengyuan Zhang, Ling Yang +6
The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with perfo…