Xiaohan Ding
ML, CV, Multimodal LLM, PhD from Tsinghua University
This profile was put together from Xiaohan's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Xiaohan Ding works in AI engineering and ML & data science, based in Shenzhen, China. ML, CV, Multimodal LLM, PhD from Tsinghua University. Public projects on GitHub include RepLKNet-pytorch (Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)), GSM-SGD (Global Sparse Momentum SGD for pruning very deep neural networks) and RepVGG (RepVGG: Making VGG-style ConvNets Great Again), mostly written in Python.
Projects 6
RepLKNet-pytorch
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)
github.com- github.com
GSM-SGD
Global Sparse Momentum SGD for pruning very deep neural networks
RepVGG
RepVGG: Making VGG-style ConvNets Great Again
github.comACNet
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
github.comDiverseBranchBlock
Diverse Branch Block: Building a Convolution as an Inception-like Unit
github.comRepMLP
RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality (CVPR 2022)
github.com