news

EPFL professor's passion for sustainable flying and expertise in machine learning and computer vision drives innovation in green aviation design and beyond. Aerodynamic shape optimization (ASO) is a key technique in aerodynamic design aimed at enhancing an object's physical performance while adhering to specific constraints.

An AI research collaboration led by EPFL professor Alexander Mathis creates a model which provides deep insights into hand movement, which is an essential step for the development of neuroprosthetics and rehabilitation technologies.

Researchers have found that AI large language models, like GPT-4, are better at predicting what comes next than what came before in a sentence. This "Arrow of Time" effect could reshape our understanding of the structure of natural language, and the way these models understand it. Large language models (LLMs) such as GPT-4 have become indispensable for tasks like text generation, coding, operating chatbots, translation and others.

Whether it's folk music, a theater festival or game design: culture thrives on encounters between people, their works and their activities. Technology has always played an important role in this. But what are the current interdependencies between digital possibilities and cultural creation? A three-part TA-SWISS project is taking a close look at the opportunities and risks of digitalization in the cultural sector.

Researchers from EPFL have developed a next-generation miniaturized brain-machine interface capable of direct brain-to-text communication on tiny silicon chips. Brain-machine interfaces (BMIs) have emerged as a promising solution for restoring communication and control to individuals with severe motor impairments.

Are you concerned about hackers stealing your fingerprint and face data for accessing your smartphone? researchers have found numerous security flaws in Android's most privileged components before hackers do and give advice to users on how to reduce risks. researchers in computer and communication sciences are hacking and fixing Android phones before malicious hackers do.

In a collaboration with EPFL Lausanne, ETH Zurich and the University of Southern California researchers at the Paul Scherrer Institute PSI have used X-rays to look inside a microchip with higher precision than ever before. The image resolution of 4 nanometres marks a new world record. The high-resolution three-dimensional images of the type they produced will enable advances in both information technology and the life sciences.

Researchers at Eawag and the Swiss Data Science Center have trained AI algorithms with a comprehensive ecotoxicological dataset. Now their machine learning models can predict how toxic chemicals are to fish. Chemicals play an important role in our everyday lives, for example in the production of food, medicines and various everyday goods.

Researchers at EPFL have made a breakthrough in understanding how neural network-based generative models perform against traditional data sampling techniques in complex systems, unveiling both challenges and opportunities for AI's future in data generation. The world of artificial intelligence (AI) has recently seen significant advancements in generative models, a type of machine-learning algorithms that "learn" patterns from set of data in order to generate new, similar sets of data.

The patchy fossil record makes it difficult for paleontologists to draw an accurate picture of the extent of past biodiversity and to understand how it has changed over time. A study led by Rebecca Cooper and Daniele Silvestro from the University of Fribourg shows how artificial intelligence (AI) can make this task easier .

Artificial intelligence (AI) combined with a novel bio-inspired camera achieves 100 times faster detection of pedestrians and obstacles than current automotive cameras. This important step for computer vision and AI achieved by researchers can greatly improve the safety of automotive systems and self-driving cars.

Researchers at EPFL have developed scalable photonic integrated circuits, based on lithium tantalate, marking a significant advancement in optical technologies with potential to widespread commercial applications. The rapid advancement in photonic integrated circuits (PICs), whichcombine multiple optical devices and functionalities on a single chip, has revolutionized optical communications and computing systems.

Researchers have used a genetic learning algorithm to identify optimal pitch profiles for the blades of vertical-axis wind turbines, which despite their high energy potential, have until now been vulnerable to strong gusts of wind. If you imagine an industrial wind turbine, you likely picture the windmill design, technically known as a horizontal-axis wind turbine (HAWT).

Automated building systems offer a great potential for reducing the energy consumption of properties. Studies on such systems show that optimized solutions can reduce the energy requirements of buildings by around 30 percent on average. In order to avoid the necessity to produce new and emission-heavy computer chips, Empa researcher Hanmin Cai is currently investigating the extent to which damaged smartphones that are no longer used could perform these control and maintenance tasks.

Researchers have shown that large language models primarily trained on English text seem to use English internally, even when they are prompted in another language. As AI increasingly runs our lives, this may have important consequences regarding linguistic and cultural bias. Large language models (LLMs) including Open AI's ChatGPT and Google's Gemini have taken the world by storm, surprising with their ability to understand and respond to users with seemingly natural speech.

Deep neural networks have achieved remarkable results across science and technology, but it remains largely unclear what makes them work so well. A new study sheds light on the inner workings of deep learning models that learn from relational datasets, such as those found in biological and social networks.

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.

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 from the Universities of Bordeaux and Lausanne have just published a study showing that the time spent playing video games has no influence on the quality of life of adult gamers.

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.