One belief underlying the power-hungry approach to machine learning advanced by OpenAI and Mistral AI is that an artificial intelligence model must review its entire dataset before spitting out new insights. Sepp Hochreiter, an early pioneer of the technology who runs an AI lab at Johannes Kepler University in Linz, Austria, has a different view, one that requires far less cash and computing power. He's interested in teaching AI models how to efficiently forget. Hochreiter holds a special place in the world of artificial intelligence, having scaled the technology's highest peaks long before most computer scientists. As a university student in Munich during the 1990s, he came up with the conceptual framework that underpinned the first generation of nimble AI models used by Alphabet, Apple and Amazon.

The advent of generative artificial intelligence (GAI) has brought about a notable surge in the field of education. The use of GAI to support learning is becoming increasingly prevalent among students. However, the manner and extent of its utilisation vary considerably from one individual to another. And researches about student's utilisation and perceptions of GAI remains relatively scarce. To gain insight into the issue, this paper proposed a hybrid-survey method to examine the impact of GAI on students across four different grades in six key areas (LIPSAL): learning interest, independent learning, problem solving, self-confidence, appropriate use, and learning enjoyment. Firstly, through questionnaire, we found that among LIPSAL, GAI has the greatest impact on the concept of appropriate use, the lowest level of learning interest and self-confidence. Secondly, a comparison of four grades revealed that the high and low factors of LIPSAL exhibited grade-related variation, and college students exhibited a higher level than high school students across LIPSAL. Thirdly, through interview, the students demonstrated a comprehensive understanding of the application of GAI. We found that students have a positive attitude towards GAI and are very willing to use it, which is why GAI has grown so rapidly in popularity. They also told us prospects and challenges in using GAI. In the future, as GAI matures technologically, it will have an greater impact on students. These findings may help better understand usage by different students and inform future research in digital education.

The rise of multimodal generative AI is transforming the intersection of technology and art, offering deeper insights into large-scale artwork. Although its creative capabilities have been widely explored, its potential to represent artwork in latent spaces remains underexamined. We use cutting-edge generative AI, specifically Stable Diffusion, to analyze 500 years of Western paintings by extracting two types of latent information with the model: formal aspects (e.g., colors) and contextual aspects (e.g., subject). Our findings reveal that contextual information differentiates between artistic periods, styles, and individual artists more successfully than formal elements. Additionally, using contextual keywords extracted from paintings, we show how artistic expression evolves alongside societal changes. Our generative experiment, infusing prospective contexts into historical artworks, successfully reproduces the evolutionary trajectory of artworks, highlighting the significance of mutual interaction between society and art. This study demonstrates how multimodal AI expands traditional formal analysis by integrating temporal, cultural, and historical contexts.

Deep generative models (DGMs) have recently demonstrated remarkable success in capturing complex probability distributions over graphs. Although their excellent performance is attributed to powerful and scalable deep neural networks, it is, at the same time, exactly the presence of these highly non-linear transformations that makes DGMs intractable. Indeed, despite representing probability distributions, intractable DGMs deny probabilistic foundations by their inability to answer even the most basic inference queries without approximations or design choices specific to a very narrow range of queries. To address this limitation, we propose probabilistic graph circuits (PGCs), a framework of tractable DGMs that provide exact and efficient probabilistic inference over (arbitrary parts of) graphs. Nonetheless, achieving both exactness and efficiency is challenging in the permutation-invariant setting of graphs. We design PGCs that are inherently invariant and satisfy these two requirements, yet at the cost of low expressive power. Therefore, we investigate two alternative strategies to achieve the invariance: the first sacrifices the efficiency, and the second sacrifices the exactness. We demonstrate that ignoring the permutation invariance can have severe consequences in anomaly detection, and that the latter approach is competitive with, and sometimes better than, existing intractable DGMs in the context of molecular graph generation.

In a blog post spotted by The Verge, the company this week published its response to President Trump's AI Action Plan. Announced at the end of February, the initiative saw the White House seek input from private industry, with the goal of eventually enacting policy that will work to "enhance America's position as an AI powerhouse" and enable innovation in the sector. "America's robust, balanced intellectual property system has long been key to our global leadership on innovation. In the same document, the company recommends the US maintain tight export controls on AI chips to China. It also says the US government should broadly adopt AI tools.

The automated future just lurched a few steps closer. Over the past few weeks, nearly all of the major AI firms--OpenAI, Anthropic, Google, xAI, Amazon, Microsoft, and Perplexity, among others--have announced new products that are focused not on answering questions or making their human users somewhat more efficient, but on completing tasks themselves. They are being pitched for their ability to "reason" as people do and serve as "agents" that will eventually carry out complex work from start to finish. Humans will still nudge these models along, of course, but they are engineered to help fewer people do the work of many. Last month, Anthropic launched Claude Code, a coding program that can do much of a human software developer's job but far faster, "reducing development time and overhead."

An original photograph taken by Felice Frankel (left) and an AI-generated image of the same content. For over 30 years, science photographer Felice Frankel has helped MIT professors, researchers, and students communicate their work visually. Throughout that time, she has seen the development of various tools to support the creation of compelling images: some helpful, and some antithetical to the effort of producing a trustworthy and complete representation of the research. In a recent opinion piece published in Nature magazine, Frankel discusses the burgeoning use of generative artificial intelligence (GenAI) in images and the challenges and implications it has for communicating research. On a more personal note, she questions whether there will still be a place for a science photographer in the research community.

Tech companies have long claimed that simply expanding their current AI models will lead to artificial general intelligence (AGI), which can match or surpass human capabilities. But as the performance of the most recent models has plateaued, AI researchers doubt that today's technology will lead to superintelligent systems. In a survey of 475 AI researchers, about 76 per cent of respondents said it was "unlikely" or "very unlikely" that scaling up current approaches will succeed in achieving AGI. The findings are part of a report by the Association for the Advancement of Artificial Intelligence, an international scientific society based in Washington DC. This is a notable change in attitude from the "scaling is all you need" optimism that has spurred tech companies since the start of the generative AI boom in 2022.

AI expert Marva Bailer explains how, even though there are currently laws in place, the average person has more access than ever to create deepfakes of celebrities. Scarlett Johansson has taken a vocal stand on artificial intelligence, after having her likeness and voice used without permission. Last year, Johansson said she had been asked to voice OpenAI's Chatbot by CEO Sam Altman, but turned down the job, only for people to notice that the feature, named "Sky," sounded almost exactly like the actress. It was like: If that can happen to me, how are we going to protect ourselves from this? There's no boundary here; we're setting ourselves up to be taken advantage of," the 40-year-old told InStyle Magazine earlier this month. In a statement to NPR following the release of "Sky," Johansson said, "When I heard the released demo, I was shocked, angered and in disbelief that Mr. Altman would pursue a voice that sounded so eerily similar to mine that my closest friends and news outlets could not tell the difference.

The rise of Generative AI (GenAI) has sparked significant debate over balancing the interests of creative rightsholders and AI developers. As GenAI models are trained on vast datasets that often include copyrighted material, questions around fair compensation and proper attribution have become increasingly urgent. To address these challenges, this paper proposes a framework called \emph{Content ARCs} (Authenticity, Rights, Compensation). By combining open standards for provenance and dynamic licensing with data attribution, and decentralized technologies, Content ARCs create a mechanism for managing rights and compensating creators for using their work in AI training. We characterize several nascent works in the AI data licensing space within Content ARCs and identify where challenges remain to fully implement the end-to-end framework.