Slurmtop is a refreshing and intuitive terminal user interface for monitoring SLURM clusters

Collaborative documentation for and from Jean Zay users. Official Jean Zay documentation: http://www.idris.fr/eng/jean-zay/

A JAX-based simulator for autonomous driving research.

A 3DGS framework for omni urban scene reconstruction and simulation.

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

4M: Massively Multimodal Masked Modeling

Official Github Repo for GEM

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Large Driving Models

SEED-Voken: A Series of Powerful Visual Tokenizers

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

FQGAN: Factorized Visual Tokenization and Generation

A partial implementation of Generative Infinite Vocabulary Transformer (GIVT) from Google Deepmind, in PyTorch.

Adaptation of vision-language models (CLIP) to downstream tasks using local and global prompts.

My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Code implementation of our NeurIPS 2023 paper: Vocabulary-free Image Classification

An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

Referring Expression Datasets API

Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

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

unofficial MaskGIT reproduction in PyTorch

An open-source framework for training large multimodal models.

Implementation of MagViT2 Tokenizer in Pytorch

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

[CVPR 2024 Highlight] Visual Point Cloud Forecasting

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"