activity
20242026
collaborators

15 papers

cs.AI2026

CATO: Charted Attention for Neural PDE Operators

Chun-Wun Cheng, Sifan Wang, Carola-Bibiane Schönlieb +1

Neural operators have emerged as powerful data-driven solvers for PDEs, offering substantial acceleration over classical numerical methods. However, existing transformer-based oper…

cs.LG2026

Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs

Chun-Wun Cheng, Jiahao Huang, Yi Zhang +3

Partial differential equations (PDEs) are widely used to model complex physical systems, but solving them efficiently remains a significant challenge. Recently, Transformers have e…

cs.CV2026

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection

Chun-Wun Cheng, Yanqi Cheng, Peiyuan Jing +4

Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution…

eess.IV2026

Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation

Chun-Wun Cheng, Yining Zhao, Yanqi Cheng +3

Image segmentation is a fundamental task in both image analysis and medical applications. State-of-the-art methods predominantly rely on encoder-decoder architectures with a U-shap…

cs.CV2026

3D Wavelet-Based Structural Priors for Controlled Diffusion in Whole-Body Low-Dose PET Denoising

Peiyuan Jing, Yue Yang, Chun-Wun Cheng +8

Low-dose Positron Emission Tomography (PET) imaging reduces patient radiation exposure but suffers from increased noise that degrades image quality and diagnostic reliability. Alth…

cs.CV2026

MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising

Peiyuan Jing, Chun-Wun Cheng, Liutao Yang +7

Low-dose Positron Emission Tomography (PET) reduces radiation exposure but suffers from severe noise and quantitative degradation. Diffusion-based denoising models achieve strong f…