Fetch an entire site and use it as an MCP Server

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Use LLM to stream diagrams, instead of tokens, in real-time! (UIST 2023 Paper)

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

You were probably looking for our website... this is it. We moved our website here, so you can see the insides of how we work.

Refine high-quality datasets and visual AI models

4DHumans: Reconstructing and Tracking Humans with Transformers

[NeurIPS 2023] Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning

Video datasets

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Extract data from all Google Scholar pages from a single Python module.

Visualize the link graph of a website.

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Aligning pretrained language models with instruction data generated by themselves.

Running large language models on a single GPU for throughput-oriented scenarios.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

MERLOT: Multimodal Neural Script Knowledge Models

A PyTorch implementation of VIOLET

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

Reverse engineered ChatGPT API

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".

A Grammar of Graphics for Python

Codes for our EMNLP2022 paper: "Learning a Grammar Inducer by Watching Millions of Instructional YouTube Videos"

Official JAX Implementation of Monocular Dynamic View Synthesis: A Reality Check (NeurIPS 2022)

Transformer related optimization, including BERT, GPT