Xilin Zhu
ContactAvailable for work
← All work

Coursework · Karlsruhe Institute of Technology (KIT)

AI and Computer Vision Project Work

Generative models and Transformer vision components, written from scratch

2025.04 — 2025.08

PyTorch implementations of a generative model and the core components of a Transformer vision architecture, covering the full path from building to training to inference.

Approach

  • A PyTorch-based GAN for handwritten digit generation on MNIST
  • Core Vision Transformer components implemented from scratch
  • Pretrained ViT-based image inference explored

Why it stays here

This is the lightest of the six projects, and its value is the foundation rather than the outcome: attention, patch embedding, and adversarial training are one thing to read about and another to write. When later work moved into VLA territory, that layer did not need relearning.