collaborators

9 papers

cs.CL2026

Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

ZiYi Dong, Yuliang Huang, Weijian Deng +3

This work reformulates language generation as a stochastic optimal control problem, providing a unified theoretical perspective to analyze autoregressive and diffusion models and e…

cs.CV2026

When Preference Labels Fall Short: Aligning Diffusion Models from Real Data

Weiyan Chen, Weijian Deng, Yao Xiao +5

Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existing approaches rely on prefere…

cs.CV2026

Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy

Qing Zhao, Weijian Deng, Pengxu Wei +4

To improve detection robustness in adverse conditions (e.g., haze and low light), image restoration is commonly applied as a pre-processing step to enhance image quality for the de…

cs.CV2026

Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection

Yao Xiao, Weiyan Chen, Jiahao Chen +8

Current AI-Generated Image (AIGI) detection approaches predominantly rely on binary classification to distinguish real from synthetic images, often lacking interpretable or convinc…

cs.CV2025

A Large-scale Dataset for Robust Complex Anime Scene Text Detection

Ziyi Dong, Yurui Zhang, Changmao Li +2

Current text detection datasets primarily target natural or document scenes, where text typically appear in regular font and shapes, monotonous colors, and orderly layouts. The tex…

cs.CV2025

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions

ZiYi Dong, Chengxing Zhou, Weijian Deng +3

Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The…