Youssef Mroueh

Jerret Ross

Brian Belgodere

Peter Hess

Inkit Padhi

Mathias Steiner

Payel Das

Leo Gross

Jason Crain

 Vijil Chenthamarakshan

Kim Martineau

Tim Erdmann

Jed Pitera

Daniel P. Sanders

Kristin Schmidt

Young-Hye Na

Maxwell Giammona

Florian Albrecht

News

Research

Technical note

Explainer

An AI foundation model that learns the grammar of molecules 

Resolving the first anti-aromatic carbon allotrope

Resolving the odd-number cyclo[13]carbon

A new tool for accelerating the discovery of new materials

Meet IBM’s new family of AI models for materials discovery

Computer simulations identify new ways to boost the skin’s natural protectors

Accelerating discovery for societal and economic impact

We're looking to accelerate the discovery process, using new AI methods, the hybrid cloud, and quantum computers, to unlock new properties and materials.

Materials Discovery

Featured work

Project Photoresist

We're developing technological solutions to assist subject matter experts with their scientific workflows by enabling the Human-AI co-creation process.  

Accelerator Technologies

NeurIPS 2024

AAAI 2025

Responsible Technology

Foundation Models

Generative AI

Physical Sciences

Life Sciences

Science

Healthcare

Climate and Sustainability

Accelerated Discovery

To respond to the global climate emergency, we're using AI and hybrid cloud to accelerate discovery of climate mitigation and adaption solutions. We're improving carbon emission performance through optimization and capture, and preparing enterprises for the impact of climate change.

Using AI and the hybrid cloud to accelerate the discovery of climate mitigation and adaption solutions to respond to the growing global climate emergency.

The combination of increasingly powerful computers and AI offers the possibility to be able to detect, diagnose, and cure diseases like never before. At IBM Research, we’re working on creating software and AI systems that can convert reams of health data into useable information for clinicians the world over.

Healthcare and Life Sciences

We're building systems that can convert reams of health data into useable information for clinicians the world over.

For AI to be useful, it needs to understand what’s being asked of it, and to know how to respond. At IBM Research, we’re working on systems to help AI better reason with the tasks it’s presented, such as understanding context and analogies, comprehension, and planning through scenarios. 

Knowledge and Reasoning

It can take over 10 years to come up with new materials. At IBM Research, we’re looking to accelerate the discovery process using new AI methods, robotics, the hybrid cloud, and quantum computers. Our goal is to unlock new properties and materials to address global challenges in years not decades.

The hybrid cloud can help businesses tap into the potential of the cloud, while retaining the benefits of private environments. At IBM Research, we’re pursuing open-source standards and code to create an agile and scalable platform that can be deployed anywhere.

Hybrid Cloud Platform

Accelerating discovery of more sustainable materials through AI and automation

A morphing .gif of molecules ranging from illustration to 3d models in a blue hue.

On the left is an unlabeled molecular structure diagram. On the right is a stack of three patent documents, and the top one has several molecular structures, including the one shown on the left. That one is highlighted in green.

Materials Discovery

Our work

Meet IBM’s new family of AI models for materials discovery

A new tool for accelerating the discovery of new materials

Resolving the odd-number cyclo[13]carbon

Resolving the first anti-aromatic carbon allotrope

An AI foundation model that learns the grammar of molecules

Accelerating discovery for societal and economic impact

Projects

Accelerator Technologies

Publications

MDLab: AI frameworks for Carbon Capture and Battery Materials

Uncertainty Analysis in Predicting Molecular Properties Using Chemical Foundation Models

Improving electrolyte performance for target cathode loading using an interpretable data-driven approach

Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry

A Large Encoder-Decoder Polymer-Based Foundation Model

A Mamba-Based Foundation Model for Chemistry

Project Photoresist

Related topics