AI generates first complete models of proteins in motion
18 May, 2026
EPFL researchers have used a neural network to create all-atom models of proteins, as well as the dynamic movements that govern their function. Their comprehensive yet simplified approach resolves a major bottleneck in biology.
New AI closes data gaps and shows how extreme weather emerges on Earth
13 May, 2026
Gaps in data and difficult‑to‑compare datasets limit what climate and weather AI models can reliably predict. Researchers from the ETH Domain have now introduced an AI model that helps close these gaps, reconstructs satellite images, and sheds light on how weather, land and water interact.
An EPFL-led study shows how language models can guide chemical synthesis and explain reactions using plain-language instructions.
A concept illustration of the development of Synthegy. Credit: Ella Maru Studio.(more…)
Read more
Drones and AI help cities combat traffic congestion
27 April, 2026
Traffic jams are a problem in large urban areas. How can they be solved without expanding the road network? This is a challenge that researchers are attempting to address.
EPFL researchers successfully mimic dyslexia in an AI brain
23 April, 2026
For the first time researchers have used an advanced AI model that understands both images and language allowing them to model dyslexia, paving the way for potential new treatments.
With AI, the voice has acquired a new significance. Behind the words lies data that can be used both to diagnose a health problem and to steal someone’s identity.
A new framework developed by EPFL researchers makes it possible to teach a skill to robots with different mechanical designs, allowing them to carry out the same task safely without rewriting code for each.
As part of the Week of Action Against Racism, EPFL is exploring the issue of algorithmic discrimination. Ahead of a public conference on campus dedicated to the topic, we’ve taken a closer look at the “black box.”
Multiple languages, sensitive documents, and strict privacy rules: for employees of the Canton of Ticino, automated translation is not trivial. The administration is now in the process of introducing an in-house translation system based on Switzerland’s Apertus—keeping both sensitive data and the underlying technology under its own control.
