(PINNs) – Physics Informed Neural Networks: Algorithms, Theory, and Applications

(PINNs) – Physics Informed Neural Networks: Algorithms, Theory, and Applications, MSML2020 Invited Talk by Prof. George Karniadakis, Brown University

Looking beyond natural sequences 27/08/2026

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

Lillian Eden | Department of Biology

AI helps design new materials that work in the real world 26/08/2026

The “CrysVCD” tool developed at MIT could cut the huge amounts of time and money spent on screening out chemically unstable designs.

Zach Winn | MIT News

Generating scenarios for extreme events, without extreme data 24/08/2026

A new algorithm learns to anticipate the unprecedented scenarios that critical infrastructure and global supply chains are least prepared for.

Jennifer Chu | MIT News

Looking beyond natural sequences 27/08/2026

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

Lillian Eden | Department of Biology

Cells use a little-known molecule to protect themselves from iron overload 25/08/2026

This discovery points toward new combination strategies against cancer, and may explain the iron buildup seen in disorders such as early-onset Parkinson’s disease.

Shafaq Zia | Whitehead Institute

How the Toxoplasma parasite adapts to crowded conditions in host cells 19/08/2026

A new study by Whitehead Institute researchers identifies how the widespread parasite Toxoplasma gondii survives in crowded environments in infected cells, which helps it persist in long-lasting brain cysts.

Mackenzie White | Whitehead Institute