activity
20242026
collaborators

5 papers

cs.CV2026

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

Xingtong Ge, Yi Zhang, Yushi Huang +6

Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency d…

cs.CV2026

Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models

Dailan He, Guanlin Feng, Xingtong Ge +6

Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching model…

cs.CV2025

Towards Seamless Borders: A Method for Mitigating Inconsistencies in Image Inpainting and Outpainting

Xingzhong Hou, Jie Wu, Boxiao Liu +5

Image inpainting is the task of reconstructing missing or damaged parts of an image in a way that seamlessly blends with the surrounding content. With the advent of advanced genera…

cs.CV2025

ADT: Tuning Diffusion Models with Adversarial Supervision

Dazhong Shen, Guanglu Song, Yi Zhang +5

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict dif…

cs.CV2024

See Further When Clear: Curriculum Consistency Model

Yunpeng Liu, Boxiao Liu, Yi Zhang +4

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model t…