news

Researchers at EPFL have developed a new, uniquely modular machine learning model for flexible decision-making. It is able to input any mode of text, video, image, sound, and time-series and then output any number, or combination, of predictions. We've all'heard of Large Language Models, or LLMs - massive scale deep learning models trained on huge amounts of text that form the basis for chatbots like OpenAI's ChatGPT.

An international collaboration between EPFL and the University of Glasgow has led to an advanced machine-learning algorithm to effectively detect concealed manufacturing defects in wind turbine composite blades - before turbines are put into service. Faulty wind turbine blades can incur huge costs for the companies that operate them, especially if the defects go unnoticed until it's too late.

Exploring the post-translational modifications of a key protein in Parkinson's disease, researchers at EPFL and USC uncover potential pathways for future therapies in neurodegenerative diseases in general. Neurodegenerative diseases, such as Alzheimer's and Parkinson's, present a significant health challenge, affecting over 50 million people globally.

Scientists have achieved a milestone by controlling quantum phenomena at room temperature. Image: Conceptual art of the operating device, consisting of a nanopillar-loaded drum sandwiched by two periodically segmented mirrors, allowing the laser light to strongly interact with the drum quantum mechanically at room temperature.

Scientists at EPFL demonstrate how GPT-3 can transform chemical analysis, making it faster and more user-friendly. Artificial intelligence is growing into a pivotal tool in chemical research, offering novel methods to tackle complex challenges that traditional approaches struggle with. One subtype of artificial intelligence that has seen increasing use in chemistry is machine learning, which uses algorithms and statistical models to make decisions based on data and perform tasks that it has not been explicitly programmed for.

Researchers have developed a machine learning approach to compressing image data with greater accuracy than learning-free computation methods, with applications for retinal implants and other sensory prostheses. A major challenge to developing better neural prostheses is sensory encoding: transforming information captured from the environment by sensors into neural signals that can be interpreted by the nervous system.

Researchers reveal a novel method to uncover bits of our genetic blueprint that come from ancient genetic parasites, offering fresh insights into human evolution and health. The human genome, an intricate tapestry of genetic information for life, has proven to be a treasure trove of strange features.

Physicists propose a novel way to create photoconductive circuits, where the circuit is directly patterned onto a glass surface with femtosecond laser light. The new technology may one day be useful for harvesting energy, while remaining transparent to light and using a single material. What happens when you expose tellurite glass to femtosecond laser light?

Scientists at EPFL break new ground in quantum physics, revealing a mysterious and unique behavior in a quantum magnetic material and hinting at future tech breakthroughs. In the mysterious world of quantum materials, things don't always behave as we expect. These materials have unique properties governed by the rules of quantum mechanics, which often means that they can perform tasks in ways traditional materials cannot - like conducting electricity without loss - or having magnetic properties that may prove useful in advanced technologies.

A new study has produced the first cost estimate of the impact that urban heat islands have on human health. The study looked at 85 European cities over the course of three full years, meaning it also took into account the protection that heat islands offer in winter - an aspect that has been little studied until now.

Scientists unveil a groundbreaking method using biological nanopores and deep learning to detect protein modifications, offering new avenues in disease diagnostics. Proteins, the workhorses of the cell, undergo various modifications after their synthesis. Because they can profoundly affect how a protein operates in the cell, these "post-translational modifications", or PTMs, are key in numerous biological processes.

An AI program can train neural networks, using just a handful of images, to rapidly characterize in satellite and drone data new objects like ocean debris, deforestation zones, urban areas and more. Images taken by drones and satellites give scientists a wealth of information. These snapshots provide crucial insight into the changes taking place on the Earth's surface, such as in animal populations, vegetation, debris floating on the ocean surface and glacier coverage.

Researchers at EPFL and Max Plank have merged nonlinear optics with electron microscopy, unlocking new capabilities in material studies and the control of electron beams. When light goes through a material, it often behaves in unpredictable ways. This phenomenon is the subject of an entire field of study called "nonlinear optics", which is now integral to technological and scientific advances from laser development and optical frequency metrology, to gravitational wave astronomy and quantum information science.

Researchers from EPFL have resolved a long-standing debate surrounding laser additive manufacturing processes with a pioneering approach to defect detection. The progression of laser additive manufacturing - which involves 3D printing of metallic objects using powders and lasers - has often been hindered by unexpected defects.

Scientists at EPFL have developed stable orally available cyclic peptides with a much higher bioavailability than current ones, virtually creating a generation of drugs that can target previously untreatable diseases like certain types of cancer. For decades, a substantial number of proteins, vital for treating various diseases, have remained elusive to oral drug therapy.

Transformative research at EPFL introduces CAR-T cells that flourish in tumor environments, paving the way for unparalleled advancements in cancer immunotherapy. At EPFL's School of Engineering, Professor Li Tang's Laboratory of Biomaterials for Immunoengineering has made significant strides in cancer treatment research.

Nearly a quarter of the Earth's land surface is permanently frozen. These areas, known as permafrost, are found in northern polar regions and at high altitudes.

In a study comparing human brain communication networks with those of macaques and mice, researchers found that only the human brains transmitted information via multiple parallel pathways, yielding new insights into mammalian evolution. When describing brain communication networks, EPFL senior postdoctoral researcher Alessandra Griffa likes to use travel metaphors.

Researchers have developed a hybrid device that significantly improves existing, ubiquitous laser technology. The team at EPFL's Photonic Systems Laboratory (PHOSL) has developed a chip-scale laser source that enhances the performance of semiconductor lasers while enabling the generation of shorter wavelengths.

A team of astronomers has used asteroseismology, or the study of stellar oscillations, to accurately measure the distance of stars from the Earth. Their research examined thousands of stars and checked the measurements taken during the Gaia mission to study the near Universe. For most of us, the countless bright spots in the nighttime sky all seem to be stars.