Generative AI Research Resources

NEW: Institutional Efforts to Help Academic Researchers Implement Generative AI in Research by Jing Liu and H. V. Jagadish

Welcome to the MIDAS generative AI resource hub. This page is curated to serve researchers looking to integrate generative AI into their work.

generative AI models, capable of creating novel, diverse, and coherent content, are revolutionizing numerous domains. They’ve demonstrated their capabilities in fields as diverse as art, music, chemistry, drug discovery, and many more. This hub is in its initial stage, and will be updated frequently. Given the rapid advance of generative AI, it is not possible for us to build a comprehensive collection. In addition to generative AI overviews and a list of the most common models, we will focus on featuring examples of how generative AI is used in research; specialized, “research-use” generative AI models, as well as models and studies developed by U-M researchers. Please get in touch if you’d like to have your model or research study using generative AI included in our collection.

Last Updated: 9/12/2024

Generative AI Overview

Generative AI in Plain English

A Brief Introduction to GenAI
K. Reid & J. Liu, Michigan Institute for Data & AI in Society.

What are Generative AI models?
IBM Technology

What are Large Language Models (LLMs)?
Google for Developers

What Is ChatGPT Doing … and Why Does It Work?
Stephen Wolfram (2023). Stephen Wolfram Writings.

A Very Gentle Introduction to Large Language Models Without the Hype
Mark Riedl (2023). Medium.

A Comprehensive Survey of Large Language Models
Cobus Greyling (2023), Medium.

Generative AI in Technical Terms

On the opportunities and risks of foundation models.
Rishi Bommasani, et al., arXiv preprint arXiv:2108.07258 (2021).

ChatGPT is not all you need. A State of the Art Review of large Generative AI models
Roberto Gozalo-Brizuela and Eduardo C. Garrido-Merch´an. arXiv preprint arXiv (2023)

Natural Language Processing with Transformers, Revised Edition.
Lewis Tunstall, Leandro von Werra, Thomas Wolf (2022).

Attention is all you need.
Ashish Vaswani, et al., Advances in neural information processing systems 30 (2017).

Fine-tuning language models from human preferences.
Daniel M. Ziegler, et al., arXiv preprint  (2019).

Examples of Research Use of Generative AI

Research Using Generative AI

Efficient evolution of human antibodies from general protein language models.
Brian Hie, et al. Nature Biotechnology (2023)

Large language models generate functional protein sequences across diverse families.
Ali Madani, et al. Nature Biotechnology (2023)

Atomic structure generation from reconstructing structural fingerprints.
Victor Fung, et al., Machine Learning: Science and Technology (2022)

Deep generative molecular design reshapes drug discovery.
Xiangxiang Zeng, et al., Cell Reports Medicine (2022)

Accelerating drug target inhibitor discovery with a deep generative foundation model.
Vijil Chenthamarakshan et al., Science Advances (2023)

Combining generative artificial intelligence and on-chip synthesis for de novo drug design.
Francesca Grisoni, et al. Science Advances (2021)

Designing Chemical Reaction Arrays using phactor and ChatGPT. 
Babak Mahjour et al. ChemRxiv (2023)

polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics.
Christopher Kuenneth and Rampi Ramprasad, Nature Communications (2023)

A Selection of Other Online Resources

AI Tools – A curated list by the University of Michigan of popular AI tools for a variety of applications, including: content, images, video, programming, productivity, and research.

AwesomeLLM – A curated list of LLMs from a technical and AI-focused perspective.

Generative AI Essentials Course – GenAI course by the University of Michigan Center for Academic Innovation.

HuggingFace LLM Leaderboard – Generative AI, and especially LLMs, are evolving rapidly. A curated list of top LLMs on a set of benchmarks can be found here.

Papers with Code – A collection of Generative AI (and non-Generative AI) papers with examples of code, datasets and more. A useful resource for seeing Generative AI applications in research.

Prompt Engineering for ChatGPT – How to apply prompt engineering effectively with ChatGPT.

Stanford Helm – “Holistic Evaluation of Language Models (HELM) is a living benchmark that aims to improve the transparency of language models.”

thepi.pe – “The thepi.pe platform provides a user-friendly interface for scraping and extracting data from various sources” – this page compares LLM evaluations.