Researchers found that vision-language models, widely used to analyze medical images, do not understand negation words like 'no' and 'not.' This could cause them to fail unexpectedly when asked to retrieve medical images that contain certain objects but not others.

Listen to the first notes of an old, beloved song. Can you name that tune? If you can, congratulations -- it's a triumph of your associative memory, in which one piece of information (the first few notes) triggers the memory of the entire pattern (the song), without you actually having to hear the rest of the song again. We use this handy neural mechanism to learn, remember, solve problems and generally navigate our reality.

A new study outlines how artificial intelligence-powered handwriting analysis may serve as an early detection tool for dyslexia and dysgraphia among young children.

Scientists inspired by the octopus's nervous system have developed a robot that can decide how to move or grip objects by sensing its environment.

Researchers have developed a digital laboratory (dLab) system that fully automates the material synthesis and structural, physical property evaluation of thin-film samples. With dLab, the team can autonomously synthesize thin-film samples and measure their material properties. The team's dLab system demonstrates advanced automatic and autonomous material synthesis for data- and robot-driven materials science.

Engineers built E-BAR, a mobile robot designed to physically support the elderly and prevent them from falling as they move around their homes. E-BAR acts as a set of robotic handlebars that follows a person from behind, allowing them to walk independently or lean on the robot's arms for support.

A robotic hand can pick up 24 different objects with human-like movements that emerge spontaneously, thanks to compliant materials and structures rather than programming.

Engineers have taught a simple submarine robot to take advantage of turbulent forces to propel itself through water.

Engineers developed a ping-pong-playing robot that quickly estimates the speed and trajectory of an incoming ball and precisely hits it to a desired location on the table.

A team of researchers has unveiled a cutting-edge Amphibious Robotic Dog capable of roving across both land and water with remarkable efficiency.

An edible robot leverages a combination of biodegradable fuel and surface tension to zip around the water's surface, creating a safe -- and nutritious -- alternative to environmental monitoring devices made from artificial polymers and electronics.

What makes people think an AI system is creative? New research shows that it depends on how much they see of the creative act. The findings have implications for how we research and design creative AI systems, and they also raise fundamental questions about how we perceive creativity in other people.

A research team develops disinfection robot combining physical wiping and UV-C sterilization.

While service robots with male characteristics can be more persuasive when interacting with some women who have a low sense of decision-making power, 'cute' design features -- such as big eyes and raised cheeks -- affect both men and women similarly, according to new research.

Researchers argue that the problem that has been lurking in the margins of many papers about touch sensors lies in the robotic skin itself.

Computer scientists have developed a new AI text-to-video model that learns real-world physics knowledge from time-lapse videos.

Researchers developed a framework to enable decentralized artificial intelligence-based building automation with a focus on privacy. The system enables AI-powered devices like cameras and interfaces to cooperate directly, using a new form of device-to-device communication. In doing so, it eliminates the need for central servers and thus the need for centralized data retention, often seen as a potential security weak point and risk to private data.

Researchers made a technique that improves the trustworthiness of machine-learning models, which could help improve the accuracy and reliability of AI predictions for high-stakes settings such health care.

While exploring a digitally represented object through artificially created sense of touch, brain-computer interface users described the warm fur of a purring cat, the smooth rigid surface of a door key and cool roundness of an apple.

Many products in the modern world are in some way fabricated using computer numerical control (CNC) machines, which use computers to automate machine operations in manufacturing. While simple in concept, the ways to instruct these machines is in reality often complex. A team of researchers has devised a system to demonstrate how to mitigate some of this complexity.

Humans are better than current AI models at interpreting social interactions and understanding social dynamics in moving scenes. Researchers believe this is because AI neural networks were inspired by the infrastructure of the part of the brain that processes static images, which is different from the area of the brain that processes dynamic social scenes.

Researchers developed a more efficient way to control the outputs of a large language model, guiding it to generate text that adheres to a certain structure, like a programming language, and remains error free.

Inspired by the movements of a tiny parasitic worm, engineers have created a 5-inch soft robot that can jump as high as a basketball hoop. Their device, a silicone rod with a carbon-fiber spine, can leap 10 feet high even though it doesn't have legs. The researchers made it after watching high-speed video of nematodes pinching themselves into odd shapes to fling themselves forward and backward.

Researchers have developed a new robotic framework powered by artificial intelligence -- called RHyME (Retrieval for Hybrid Imitation under Mismatched Execution) -- that allows robots to learn tasks by watching a single how-to video.

Researchers have developed a new artificial intelligence (AI) technique that brings machine vision closer to how the human brain processes images. Called Lp-Convolution, this method improves the accuracy and efficiency of image recognition systems while reducing the computational burden of existing AI models.

A powerful clinical artificial intelligence tool developed by biomedical informatics researchers has demonstrated remarkable accuracy on all three parts of the United States Medical Licensing Exam (Step exams), according to a new article.

A team has developed an explainable AI model for automatic collision avoidance between ships.

A groundbreaking open-source computer program uses artificial intelligence to analyze videos of patients with Parkinson's disease and other movement disorders. The tool, called VisionMD, helps doctors more accurately monitor subtle motor changes, improving patient care and advancing clinical research.

It's a game a lot of us played as children -- and maybe even later in life: unspooling measuring tape to see how far it would extend before bending. But to engineer, this game was an inspiration, suggesting that measuring tape could become a great material for a robotic gripper. The grippers would be a particularly good fit for agriculture applications, as their extremities are soft enough to grab fragile fruits and vegetables, researchers wrote. The devices are also low-cost and safe around humans.

A hopping, insect-sized robot can jump over gaps or obstacles, traverse rough, slippery, or slanted surfaces, and perform aerial acrobatic maneuvers, while using a fraction of the energy required for flying microbots.

FLUID, an open-source, 3D-printed robot, offers an affordable and customizable solution for automated material synthesis, making advanced research accessible to more scientists.

American Sign Language (ASL) recognition systems often struggle with accuracy due to similar gestures, poor image quality and inconsistent lighting. To address this, researchers developed a system that translates gestures into text with 98.2% accuracy, operating in real time under varying conditions. Using a standard webcam and advanced tracking, it offers a scalable solution for real-world use, with MediaPipe tracking 21 keypoints on each hand and YOLOv11 classifying ASL letters precisely.

A tiny, soft, flexible robot that can crawl through earthquake rubble to find trapped victims or travel inside the human body to deliver medicine may seem like science fiction, but an international team is pioneering such adaptable robots by integrating flexible electronics with magnetically controlled motion.

How does a robotic arm or a prosthetic hand learn a complex task like grasping and rotating a ball? Researchers address the classic 'nature versus nurture' question. The research demonstrates that the sequence of learning, also known as the 'curriculum,' is critical for learning to occur. In fact, the researchers note that if the curriculum takes place in a particular sequence, a simulated robotic hand can learn to manipulate with incomplete or even absent tactile sensation.

Imagine navigating a virtual reality with contact lenses or operating your smartphone under water: This and more could soon be a reality thanks to innovative e-skins. A research team has developed an electronic skin that detects and precisely tracks magnetic fields with a single global sensor. This artificial skin is not only light, transparent and permeable, but also mimics the interactions of real skin and the brain.

A new study shows that people in Japan treat robots and AI agents more respectfully than people in Western societies.

This a robot can walk, without electronics, and only with the addition of a cartridge of compressed gas, right off the 3D-printer. It can also be printed in one go, from one material.

A leaping robot could have application in search and rescue, construction, even forest monitoring. But how do you design a robot to stick a landing on a branch or pipe? Biologists worked with robot designers to discover how squirrels do it, and used what they learned to design a one-legged robot with the balancing ability and leg biomechanics to correct for over- and undershooting and land successfully on a narrow perch.

An AI-powered robot that can prepare cups of coffee in a busy kitchen could usher in the next generation of intelligent machines, a study suggests.

Chemists have created a machine learning tool that can identify the chemical composition of dried salt solutions from an image with 99% accuracy. By using robotics to prepare thousands of samples and artificial intelligence to analyze their data, they created a simple, inexpensive tool that could expand possibilities for performing chemical analysis.

Virginia Tech researchers say a true revolution in wireless technologies is only possible through endowing the system with the next generation of artificial intelligence (AI) that can think, imagine, and plan akin to humans. Doing so will allow networks to break free from traditional enablers, deliver unprecedented quality, and usher in a new phase of the AI evolution.

Engineers developed a method to grow artificial muscle tissue that twitches and flexes in multiple, coordinated directions. These tissues could be useful for building 'biohybrid' robots powered by soft, artificially grown muscle fibers.

Researchers have enabled a man who is paralyzed to control a robotic arm through a device that relays signals from his brain to a computer. He was able to grasp, move and drop objects just by imagining himself performing the actions.

Energy remains a significant factor in industrial production processes. High levels of energy consumption make production more expensive and exacerbate the climate crisis. A new type of robot technology needs 90% less electricity than conventional systems. The technology uses lightweight, shape memory materials to construct novel, non-pneumatic, industrial gripper systems that function without the need for additional sensors.

Scientists have developed a biorobotic arm that can mirror human tremors, such as those experienced by individuals that live with Parkinson's disease. Artificial muscles on either side of the forearm contract and relax to suppress the involuntary shaking of the wrist and hand. The researchers see their biorobotic arm not only as a platform for other scientists in the field to test new ideas in exoskeleton technology. The arm also serves as a test bed to see how well artificial muscles known as HASELs can one day become the building blocks of wearable devices. The vision is to one day develop a sleeve that tremor patients can comfortably wear to be able to better cope with everyday tasks such as holding a cup.

Cutting edge technology may come with downsides.

Walking into your favorite restaurant and seeing a robot chef in the kitchen may seem far-fetched, but new research suggests that bots could be a solution to persistent labor shortages in the industry.

Engineers have developed a pioneering prosthetic hand that can grip plush toys, water bottles, and other everyday objects like a human, carefully conforming and adjusting its grasp to avoid damaging or mishandling whatever it holds.

Soilless growing systems inside greenhouses, known as controlled environment agriculture, promise to advance the year-round production of high-quality specialty crops, according to an interdisciplinary research team. But to be competitive and sustainable, this advanced farming method will require the development and implementation of precision agriculture techniques. To meet that demand, the team developed an automated crop-monitoring system capable of providing continuous and frequent data about plant growth and needs, allowing for informed crop management.

Researchers have demonstrated that multicolored stickers applied to stop or speed limit signs on the roadside can 'confuse' self-driving vehicles, causing unpredictable and possibly hazardous operations.

A research team has recently developed a groundbreaking neuromorphic exposure control (NEC) system that revolutionizes machine vision under extreme lighting variations. This biologically inspired system mimics human peripheral vision to achieve unprecedented speed and robustness in dynamic perception environments.

Springtails, small bugs often found crawling through leaf litter and garden soil, are expert jumpers. Inspired by these hopping hexapods, roboticists have made a walking, jumping robot that pushes the boundaries of what small robots can do. The research glimpses a future where nimble microrobots can crawl through tiny spaces, skitter across dangerous ground, and sense their environments without human intervention.

A bioinspired robot can change shape to alter its own physical properties in response to its environment, resulting in a robust and efficient autonomous vehicle as well as a fresh approach to robotic locomotion.

A research team demonstrated the 'world's smallest shooting game,' a unique nanoscale game inspired by classic arcade games. This achievement was made possible by real-time control of the force fields between nanoparticles using focused electron beams. This research has practical applications, as the manipulation of nanoscale objects could revolutionize biomedical engineering and nanotechnology.

A team of scientists has now created a computer model that can represent and generate human-like goals by learning from how people create games. The work could lead to AI systems that better understand human intentions and more faithfully model and align with our goals. It may also lead to AI systems that can help us design more human-like games.

Most AI diagnostic tools are black boxes, but the approach allows doctors and patients to understand how the computer reached a diagnosis.

Researchers are blurring the lines between robotics and materials, with a proof-of-concept material-like collective of robots with behaviors inspired by biology.

Groundbreaking study shows machine learning can decode emotions in seven ungulate species. A game-changer for animal welfare? Can artificial intelligence help us understand what animals feel? A pioneering study suggests the answer is yes. Researchers have successfully trained a machine-learning model to distinguish between positive and negative emotions in seven different ungulate species, including cows, pigs, and wild boars. By analyzing the acoustic patterns of their vocalizations, the model achieved an impressive accuracy of 89.49%, marking the first cross-species study to detect emotional valence using AI.

A novel system that chases larval zebrafish around an arena with predator robots is enabling scientists to understand how these days-old fish quickly learn in the real world.

Engineers have developed a versatile swimming robot that nimbly navigates cluttered water surfaces. Inspired by marine flatworms, the innovative device offers new possibilities for environmental monitoring and ecological research.