Open-sourced the first public implementation of “Deep Mixture of Experts via Shallow Embedding,” a computer vision paper that previously had no available code.

Built with: PyTorch, Computer Vision

GitHub: RyanKim17920/Deep-Mixture-of-Experts-via-Shallow-Embedding

• Reproduced the full model architecture directly from the original paper with no reference implementation
• First public code release for this paper, making the architecture accessible to the research community
• Computer vision model built and validated end-to-end in PyTorch

July – November 2024