news

A new EPFL paper has found that students are cautious towards AI feedback, highlighting the complexity of integrating it into educational feedback systems. Feedback plays a crucial role in learning, helping individuals to understand and improve their performance, yet globally large and diverse student populations often mean that providing timely and personalized observations can be a challenge.

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.

An AI-powered tool developed at EPFL can distinguish dark matter's elusive effects from other cosmic phenomena, which could bring us closer to unlocking the secrets of dark matter. Image: Still image from simulation of the formation of dark matter structures from the early universe to today. Gravity makes dark matter clump into dense halos, indicated by bright patches, where galaxies form.

Researchers at EPFL unlock a detailed understanding of brain and spinal cord interactions. The tool that paves the way for future research breakthroughs and innovative therapeutic approaches. The brain and spinal cord are the central pillars of the human central nervous system (CNS), orchestrating everything from movement to sensation.

Scientists at EPFL have developed an AI tool that creates detailed models of cellular metabolism, making it easier to understand how cells function. Understanding how cells process nutrients and produce energy - collectively known as metabolism - is essential in biology. However, analyzing the vast amounts of data on cellular processes to determine metabolic states is a complex task.

Medical imaging technology - such as MRI, ultrasound and X-ray - is gaining in power and precision, especially in the wake of recent breakthroughs in artificial intelligence. Several EPFL research groups are contributing to this progress and actively shaping the future in this area. Thanks to advances in medical imaging, doctors can localize a bone fracture, detect a tumor and observe a baby inside the uterus, all'in a completely noninvasive manner.

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.

Climate change is particularly intense in the Arctic. To assess its consequences and determine what role this region plays in global warming, two teams of scientists from EPFL have visited the area. One to gain a better understanding of the region's air composition, the other to quantify the greenhouse gases sequestered in Greenland fjords sourced by glacial water.

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.

Scientists have developed an AI-based technique to improve chemical analysis of nanomaterials, overcoming challenges of noisy data and mixed signals. "Nanomaterials" is a broad term used to describe chemical substances or materials in which a single unit is sized between 1 and 100 nanometers (a nanometer is a billionth of a meter).

Extreme heatwaves are on the rise. When do they become critical for forest trees? In the hot summer of 2023, a research team led by the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) and the Swiss Federal Institute of Technology Lausanne (EPFL) investigated this in Switzerland, southern France and Spain.

A team of scientists from EPFL and other research institutes have identified just how an Alpine flower is surviving by adapting its genes to local habitats. This discovery has important implications for the protection of ecosystems under threat. In the Alps, adventurous hikers aren't the only ones to regularly climb to new heights.

Researchers a novel AI-driven model designed to predict protein sequences from backbone scaffolds, incorporating complex molecular environments. It promises significant advancements in protein engineering and applications across various fields, including medicine and biotechnology. Image caption: Schematic representation of sequence prediction with CARBonAra.

Researchers have published a programmable framework that overcomes a key computational bottleneck of optics-based artificial intelligence systems. In a series of image classification experiments, they used scattered light from a low-power laser to perform accurate, scalable computations using a fraction of the energy of electronics.

In a new study, scientists found that rhinoceros beetles use passive mechanisms to deploy and retract wings instead of muscles. The findings inspired them to design a new microrobot, demonstrating a simple, yet effective, approach to the design of insect-like flying micromachines. Birds, bats, and bees all'use distinct muscles to deploy and retract their wings.

In an important study for understanding how memories are made, scientists show that the flexibility of chromatin - packaged DNA inside the cell - plays a crucial role in "deciding" which neurons are involved in forming a specific memory. When we form a new memory, the brain undergoes physical and functional changes known collectively as a "memory trace".

Addressing problems with diagnosing and treating breast cancer, scientists at EPFL have developed EMBER, a tool that integrates breast cancer transcriptomic data from multiple databases. EMBER can improve precision oncology by accurately predicting molecular subtypes and therapy responses. Breast cancer is the most frequently diagnosed cancer worldwide.

Developed at EPFL, Heriot-Watt University, and ETH Zurich, PrISMa is a new platform that uses advanced simulations and machine learning to streamline carbon capture technologies, by taking into account the perspectives of diverse stakeholders early in the research process. Mitigating the effects of climate change has become a major focus worldwide, with countries and international organizations developing various strategies to address the problem.

Researchers at EPFL have discovered how amyloid fibrils form complex structures, shedding light on diseases like Alzheimer's and opening new doors in material science. Amyloids are protein aggregates that can form in the body, sometimes leading to diseases like Alzheimer's. These fibrils can adopt multiple shapes, known as "polymorphs", which complicate our understanding of their role in health and disease.

Researchers discovered that deepwater renewal in Lake Geneva in wintertime is not only due to vertical mixing. Instead, strong currents coming from the lake's Petit Lac basin and nearshore zones of the Grand Lac play a vital role. In temperate lakes, deep vertical mixing, known as turnover, happens during winter.