3 papers
cs.CV2025
Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation
Zijing Hu, Yunze Tong, Fengda Zhang +3
Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This…
cs.CV2025
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
Zijing Hu, Fengda Zhang, Long Chen +6
Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and c…
cs.CV2024
Distributionally Generative Augmentation for Fair Facial Attribute Classification
Fengda Zhang, Qianpei He, Kun Kuang +5
Facial Attribute Classification (FAC) holds substantial promise in widespread applications. However, FAC models trained by traditional methodologies can be unfair by exhibiting acc…