Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"

Code for “FlowMM Generating Materials with Riemannian Flow Matching” and "FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions"

EDM2 and Autoguidance -- Official PyTorch implementation

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization, with PyTorch/CUDA

Gemini is a modern LaTex beamerposter theme 🖼

Release for Improved Denoising Diffusion Probabilistic Models

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

v objective diffusion inference code for PyTorch.

Karras et al. (2022) diffusion models for PyTorch

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".

Official PyTorch implementation for "Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations"

PyTorch implementation for "Training and Inference on Any-Order Autoregressive Models the Right Way", NeurIPS 2022 Oral, TPM 2023 Best Paper Honorable Mention

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Template-based docx report creation

Pandoc filter for cross-references

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

✨✨Latest Advances on Multimodal Large Language Models

High-fidelity performance metrics for generative models in PyTorch

VQVAEs, GumbelSoftmaxes and friends

A simple Bayesian Flow model for MNIST.

This is the official code release for Bayesian Flow Networks.

A simple implimentation of Bayesian Flow Networks (BFN)

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.