activity
20242026
collaborators

5 papers

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2024

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

Zejian Li, Chenye Meng, Yize Li +9

Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in…