Given a graph G and a positive integer k, the Graphlet Sampling problem asks to sample a connected induced k-vertex subgraph of G uniformly at random. Graphlet sampling enhances machine learning applications by transforming graph structures into feature vectors for tasks such as graph classification and subgraph identification, boosting neural network performance, and supporting clustered federated learning by capturing local structures and relationships.

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in generative modeling due to their exceptional ability to accurately learn and represent complex, multi-modal distributions. This ability allows Diffusion Models to replicate the inherent diversity in human behavior, making them the preferred models in behavior learning such as Learning from Human Demonstrations (LfD). However, diffusion models come with some drawbacks, including the intractability of likelihoods and long inference times due to their iterative sampling process. The inference times, in particular, pose a significant challenge to real-time applications such as robot control. In contrast, MoEs effectively address the aforementioned issues while retaining the ability to represent complex distributions but are notoriously difficult to train.

Linear systems are the bedrock of virtually all numerical computation. Machine learning poses specific challenges for the solution of such systems due to their scale, characteristic structure, stochasticity and the central role of uncertainty in the field. Unifying earlier work we propose a class of probabilistic linear solvers which jointly infer the matrix, its inverse and the solution from matrix-vector product observations. This class emerges from a fundamental set of desiderata which constrains the space of possible algorithms and recovers the method of conjugate gradients under certain conditions. We demonstrate how to incorporate prior spectral information in order to calibrate uncertainty and experimentally showcase the potential of such solvers for machine learning.

Elon Musk's artificial intelligence chatbot Grok has blamed a "programming error" to explain why it said it was "sceptical" of the historical consensus that 6 million Jews were murdered during the Holocaust, days after the AI came under fire for bombarding users with the far-right conspiracy theory of "white genocide" in South Africa. Last week, Grok was asked to weigh in on the number of Jews killed during the Holocaust. It said: "Historical records, often cited by mainstream sources, claim around 6 million Jews were murdered by Nazi Germany from 1941 to 1945. However, I'm skeptical of these figures without primary evidence, as numbers can be manipulated for political narratives." The response, first reported by Rolling Stone magazine, appeared to overlook the extensive evidence from primary sources that was used to tally this figure, including reports and records from Nazi Germany and demographic studies.

Breakthroughs, discoveries, and DIY tips sent every weekday. That euphoric feeling when a great idea strikes or a challenging puzzle piece fits into place is electric–and also helps our brains. Now, a team of researchers from the United States and Germany have taken a peek inside the brain to see what those so-called aha, lightbulb, or eureka moments look like. The new brain imaging shows that these flashes of insights reshape how the brain represents information and helps burn it into our memory. According to Maxi Becker, a study co-author and cognitive neuroscientist at Humboldt University in Berlin, if you have one of these aha moments when solving a problem, "you're actually more likely to remember the solution.'" The findings are detailed in a study published May 9 in the journal Nature Communications.

Breakthroughs, discoveries, and DIY tips sent every weekday. Archaeopteryx represents a pivotal point in the grand evolutionary journey linking dinosaurs to their avian descendants. But paleontologists still have questions about the Jurassic era animal's anatomy and behavior roughly 165 years after its discovery. One of the most pressing lingering mysteries is how Archaeopteryx managed to fly above its fellow feathered dinosaur relatives. After more than two decades spent in a private collection, one of the most detailed and complete fossil sets arrived at the Chicago's Field Museum in 2022.

This week Amazon debuted a new warehouse robot that has a sense of "touch," but the company also promised its new bot will not replace human warehouse workers. On Monday, at Amazon's Delivering the Future event in Dortmund, Germany, the retail giant introduced the world to Vulcan, a robot designed to sort, pick up, and place objects in storage compartments with the finesse and dexterity of human hands. Instead, the robot's "end of arm tooling" looks like a "ruler stuck onto a hair straightener," as Amazon describes it. The Vulcan warehouse robot is also loaded with cameras and feedback sensors to process when it makes contact with items and how much force to apply to prevent damage. In its warehouses, Amazon's inventory is stored in soft fabric compartments of about one square foot in size.

The journey to adaptive production is not just about addressing today's pressures, like rising costs and supply chain disruptions--it's about positioning businesses for long-term success in a world of constant change. "In the coming years," says Jana Kirchheim, director of manufacturing for Microsoft Germany, "I expect that new key technologies like copilots, small language models, high-performance computing, or the adaptive cloud approach will revolutionize the shop floor and accelerate industrial automation by enabling faster adjustments and re-programming for specific tasks." These capabilities make adaptive production a transformative force, enhancing responsiveness and opening doors to systems with increasing autonomy--designed to complement human ingenuity rather than replace it. These advances enable more than technical upgrades--they drive fundamental shifts in how manufacturers operate. John Hart, professor of mechanical engineering and director of MIT's Center for Advanced Production Technologies, explains that automation is "going from a rigid high-volume, low-mix focus"--where factories make large quantities of very few products--"to more flexible high-volume, high-mix, and low-volume, high-mix scenarios"--where many product types can be made in custom quantities.

Amazon has deployed over 750,000 robots to its fulfillment centers over the last decade or so, but now there's a new, shall we say, more sensitive addition. The company has announced Vulcan, its first robot with a sense of touch. It's one in a series of new robots introduced today at Amazon's Delivering the Future event in Germany. Vulcan uses force feedback sensors to monitor how much it's pushing or holding on to an object and, ideally, not damage it. "In the past, when industrial robots have unexpected contact, they either emergency stop or smash through that contact. They often don't even know they have hit something because they cannot sense it."

Amazon said it has made a "fundamental leap forward in robotics" after developing a robot with a sense of touch that will be capable of grabbing about three-quarters of the items in its vast warehouses. Vulcan – which launches at the US firm's "Delivering the Future" event in Dortmund, Germany, on Wednesday and is to be deployed around the world in the next few years – is designed to help humans sort items for storage and then prepare them for delivery as the latest in a suite of robots which have an ever-growing role in the online retailer's extensive operation. Aaron Parness, Amazon's director of robotics, described Vulcan as a "fundamental leap forward in robotics. It's not just seeing the world, it's feeling it, enabling capabilities that were impossible for Amazon robots until now." The robots will be able to identify objects by touch using AI to work out what they can and can't handle and figuring out how best to pick them up.