Wei Fang

Algorithm Engineer

Alibaba DAMO Academy

Email: frenkyfangwe@gmail.com

Biography

I am an Algorithm Engineer at Alibaba DAMO Academy since 2022. Before that, I got my Ph.D. and B.S. degrees both from Tsinghua University. I spent one wonderful year in Harvard Medical school during my Ph.D. study. I am familar with CT physics, CT reconstruction, medical image segmentation, classification and diffusion models. I have interest in what large language models and vision-language models will bring to the healthcare industry.

News

• [2/2025] Our paper "MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers" was accepted to ICLR 2025 as spotlight and I attended the conference at Singapore.

• [03/2024] Our paper "CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data" was accepted to CVPR 2024 and I attented the conference at Seattle.

• [11/2023] Our paper "Large-scale pancreatic cancer detection via non-contrast CT and deep learning" was accepted to Nature Medicine.

• [07/2022] Our paper "Cancerunit: Towards a single unified model for effective detection, segmentation, and diagnosis of eight major cancers using a large collection of ct scans" was accepted to ICCV 2023.

• [09/2022] Our paper "Neuron with Steady Response Leads to Better Generalization" was accepted to NeurIPS 2022.

• [03/2022] Our paper "Attenuation image referenced (AIR) effective atom number image calculation for MeV dual-energy container CT using image-domain deep learning framework" was accepted to Results in Physics.

• [05/2021] Our paper "Iterative material decomposition for spectral CT using self-supervised Noise2Noise prior" was accepted to Physics in Medicine and Biology.