21 Lessons, Get Started Building with Generative AI

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

llama3 implementation one matrix multiplication at a time

High-Resolution Image Synthesis with Latent Diffusion Models

Public facing notes page

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Flax is a neural network library for JAX that is designed for flexibility.

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Machine Learning Journal for Intermediate to Advanced Topics.

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

PyTorch implementation of Soft Actor-Critic (SAC)

A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.

[NeurIPS 2025] Official repository for "Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling"

[CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing

[arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

Official implementation of "Invertible Kernel PCA with Random Fourier Features", 2022.