Farquhar, the Tech Council of Australia CEO, told ABC's 7.30 program on Tuesday: "all AI usage of mining or searching or going across data is probably illegal under Australian law and I think that hurts a lot of investment of these companies in Australia". Farquhar's claim overlooks that this is not a settled issue in the US, and could have devastating effects on creative industries. Farquhar's argument is that it is not theft of people's work unless the AI is used to "copy an artist directly" such as creating a song in their style. "I do think people would say that, hey, if people are going to sit down with a digital companion, an AI song creator and they collaboratively work with an AI to create something new to the world, that's probably fair use." Farquhar said the benefits of large language models outweigh the issues raised by AI training its data on other people's work for free.

Charts are very common for exploring data and communicating insights, but extracting key takeaways from charts and articulating them in natural language can be challenging. The chart-to-text task aims to automate this process by generating textual summaries of charts. While with the rapid advancement of large Vision-Language Models (VLMs), we have witnessed great progress in this domain, little to no attention has been given to potential biases in their outputs. This paper investigates how VLMs can amplify geo-economic biases when generating chart summaries, potentially causing societal harm. Specifically, we conduct a large-scale evaluation of geo-economic biases in VLM-generated chart summaries across 6,000 chart-country pairs from six widely used proprietary and open-source models to understand how a country's economic status influences the sentiment of generated summaries. Our analysis reveals that existing VLMs tend to produce more positive descriptions for high-income countries compared to middle- or low-income countries, even when country attribution is the only variable changed. We also find that models such as GPT-4o-mini, Gemini-1.5-Flash, and Phi-3.5 exhibit varying degrees of bias. We further explore inference-time prompt-based debiasing techniques using positive distractors but find them only partially effective, underscoring the complexity of the issue and the need for more robust debiasing strategies. Our code and dataset are publicly available here.

Many real-world interactions are group-based rather than pairwise such as papers with multiple co-authors and users jointly engaging with items. Hypergraph neural networks have shown great promise at modeling higher-order relations, but their reliance on a fixed number of explicit message-passing layers limits long-range dependency capture and can destabilize training as depth grows. In this work, we introduce Implicit Hypergraph Neural Networks (IHGNN), which bring the implicit equilibrium formulation to hypergraphs: instead of stacking layers, IHGNN computes representations as the solution to a nonlinear fixed-point equation, enabling stable and efficient global propagation across hyperedges without deep architectures. We develop a well-posed training scheme with provable convergence, analyze the oversmoothing conditions and expressivity of the model, and derive a transductive generalization bound on hypergraphs. We further present an implicit-gradient training procedure coupled with a projection-based stabilization strategy. Extensive experiments on citation benchmarks show that IHGNN consistently outperforms strong traditional graph/hypergraph neural network baselines in both accuracy and robustness. Empirically, IHGNN is resilient to random initialization and hyperparameter variation, highlighting its strong generalization and practical value for higher-order relational learning.

-- Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are unsuitable for embedded robotic devices with limited resources (such as intelligent vehicles/cars) where rapid detection is necessary to prevent accidents. This paper introduces LiteFat, a lightweight spatio-temporal graph learning model designed to detect driver fatigue efficiently while maintaining high accuracy and low computational demands. LiteFat involves converting streaming video data into spatio-temporal graphs (STG) using facial landmark detection, which focuses on key motion patterns and reduces unnecessary data processing. LiteFat uses MobileNet to extract facial features and create a feature matrix for the STG. A lightweight spatio-temporal graph neural network is then employed to identify signs of fatigue with minimal processing and low latency. Experimental results on benchmark datasets show that LiteFat performs competitively while significantly reduced computational complexity and latency as compared to current state-of-the-art methods. This work advances the development of real-time, resource-efficient human fatigue detection systems that can be implemented upon embedded robotic devices. Driver fatigue is a major contributor to traffic accidents worldwide, posing a significant threat to road safety [1].

Feedback is New Scientist's popular sideways look at the latest science and technology news. You can submit items you believe may amuse readers to Feedback by emailing feedback@newscientist.com If you want to succeed in science, it helps to have good ideas, to be good at experiments, and so forth. But what you really need is a knack for a good acronym. If you can come up with a string of words that describes your project, and also abbreviates to form a word, you're golden.

Claire's on brink of collapse putting 2,150 jobs at risk 15 minutes agoShareSaveTom EspinerBusiness reporter, BBC NewsShareSaveEPA Claire's will appoint administrators after struggles with online competition. Fashion accessories chain Claire's is on the brink of collapse after the retailer said it will appoint administrators in the UK and Ireland, putting 2,150 jobs at risk. The company has 278 stores in the UK and 28 in Ireland but has been struggling with falling sales and fierce competition. All the shops will continue trading while administrators at Interpath, once appointed, will "assess options for the company". Interpath chief executive Will Wright, said options include "exploring the possibility of a sale which would secure a future for this well-loved brand". Claire's in the US filed for bankruptcy in the US earlier this month.

I am 85 hours into Death Stranding 2, an apocalyptic nightmare about Earth becoming infected with death monsters, and I've realised that I'm playing it as a cosy game. For hours at a time, I trundle along the photorealistic landscapes in my pick-up truck, delivering parcels to isolated communities and building new roads. The only reason I complete the main story missions is to open new areas of the map so that I can meet new people and build more roads. I find it blissfully enjoyable. Of course, I am far from alone in playing video games this way.

YouTube is one of the most popular online platforms in the U.S. among all age groups. But not all content on the video-sharing site is appropriate for all ages. While the platform, like most, has restrictions on certain content, such as violence and nudity, for users under 18, these safeguards have in the past been easy for young users to circumvent by entering an older birthdate on their account. But now, the company is rolling out an artificial intelligence-powered tool to estimate a user's age based on their activity on the platform "and then use that signal, regardless of the birthday in the account, to deliver our age-appropriate product experiences and protection," said James Beser, director of product management at YouTube Youth, in blog post last month. The technology, according to Beser, has been used in other markets "for some time" and will begin being tested in the U.S. on Wednesday before a wider rollout.

AI risks entrenching racism and sexism in Australia, the human rights commissioner has warned, amid internal Labor debate about how to respond to the emerging technology. Lorraine Finlay says the pursuit of productivity gains from AI should not come at the expense of discrimination if the technology is not properly regulated. Finlay's comments follow Labor senator Michelle Ananda-Rajah breaking ranks to call for all Australian data to be "freed" to tech companies to prevent AI perpetuating overseas biases and reflect Australian life and culture. Ananda-Rajah is opposed to a dedicated AI act but believes content creators should be paid for their work. Media and arts groups have warned of "rampant theft" of intellectual property if big tech companies can take their content to train AI models.

Due to perceptions of efficiency and significant productivity gains, various organisations, including in education, are adopting Large Language Models (LLMs) into their workflows. Educator-facing, learner-facing, and institution-facing LLMs, collectively, Educational Large Language Models (eLLMs), complement and enhance the effectiveness of teaching, learning, and academic operations. However, their integration into an educational setting raises significant cybersecurity concerns. A comprehensive landscape of contemporary attacks on LLMs and their impact on the educational environment is missing. This study presents a generalised taxonomy of fifty attacks on LLMs, which are categorized as attacks targeting either models or their infrastructure. The severity of these attacks is evaluated in the educational sector using the DREAD risk assessment framework. Our risk assessment indicates that token smuggling, adversarial prompts, direct injection, and multi-step jailbreak are critical attacks on eLLMs. The proposed taxonomy, its application in the educational environment, and our risk assessment will help academic and industrial practitioners to build resilient solutions that protect learners and institutions.