Single-stage End-to-End Training for Tokenization and Generation

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre-trained weights

[ICLR 25] Code for "Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning"

Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?

🚀 Efficient implementations for emerging model architectures

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

🧱 Modula software package

Open source Structure-from-Motion pipeline