Python script to facilitate easy automatic pulling of new papers from Arxiv, Biorxiv, and Medrxiv with custom search features.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

A series of math-specific large language models of our Qwen2 series.

Multi-Agent Reinforcement Learning with JAX

A benchmarking suite for disentanglement algorithms, suited for evaluating robustness to correlated factors. Codebase for the paper "Disentanglement of Correlated Factors via Hausdorff Factorized S…

Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.

🎁 6,500,000+ Unsplash images made available for research and machine learning

Level-Based Foraging (LBF): A multi-agent reinforcement learning environment

Code repository for the paper "Attentive Group Equivariant Convolutional Neural Networks" published at ICML 2020. https://arxiv.org/abs/2002.03830

DomainBed is a suite to test domain generalization algorithms

MetaBox: Benchmarking Platform for Meta-Black-Box Optimization

A library for generative social simulation

[ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

🐟 Python profile viewer

Pytorch implementation of the xLSTM model by Beck et al. (2024)

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Code for "Generative Adversarial Training for Markov Chains" (ICLR 2017 Workshop)

Double Control Variates for Gradient Estimation in Discrete Latent Variable Models

Ongoing research training transformer models at scale

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Official repository for "Orthogonal Projection Loss" (ICCV'21)

This repository is the official implementation of Improving Object-centric Learning With Query Optimization

xLSTM as Generic Vision Backbone

Library for the training and evaluation of object-centric models (ICML 2022)