Lucas Maes

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

nano-simsiam. Minimalistic, hackable PyTorch implementation of SimSiam in ~400 lines. Achieves good performance on ImageNet with ResNet50. Features distributed training, real-time KNN eval, and AMP. Perfect for research prototyping.

learning-legged-locomotion. Learning Legged Locomotion project for the course Robot Learning - IFT6163

ijepa. Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."