Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: $\text{GeAR}$ and explore its performance and limitations on the SIGIR 2025 LiveRAG Challenge.

In the human-bot symbiotic information ecosystem, social bots play key roles in spreading and correcting disinformation. Understanding their influence is essential for risk control and better governance. However, current studies often rely on simplistic user and network modeling, overlook the dynamic behavior of bots, and lack quantitative evaluation of correction strategies. To fill these gaps, we propose MADD, a Multi Agent based framework for Disinformation Dissemination. MADD constructs a more realistic propagation network by integrating the Barabasi Albert Model for scale free topology and the Stochastic Block Model for community structures, while designing node attributes based on real world user data. Furthermore, MADD incorporates both malicious and legitimate bots, with their controlled dynamic participation allows for quantitative analysis of correction strategies. We evaluate MADD using individual and group level metrics. We experimentally verify the real world consistency of MADD user attributes and network structure, and we simulate the dissemination of six disinformation topics, demonstrating the differential effects of fact based and narrative based correction strategies.

HHS Secretary told members of Congress on Tuesday that wearables are "a way of people can take control over their own health." Have you ever noticed how a spilled cup of coffee leaves behind a telltale brown ring? While those stains might be annoying, the science behind them, known as the coffee ring effect, has sparked innovations in health technology. UC Berkeley researchers recently turned this everyday phenomenon into a breakthrough medical test, making rapid and reliable disease detection as easy as brewing your morning coffee. Curious how a simple coffee stain could inspire cutting-edge diagnostics and revolutionize at-home testing?

We write a lot about robots here at New Scientist – the latest cutting-edge developments, the newest technology. But we also have a great deal of fondness for them in fiction, whether that's the super cute likes of WALL-E and BB-8, or the darker side of the robotic family, from the Terminator to Ava from Ex Machina. Last month, Sierra Greer's novel about the rebellion of a robot designed for intimacy, Annie Bot, won this year's Arthur C Clarke award, the UK's top prize for science fiction. It was described by judges as "a tightly-focused first person account of a robot designed to be the perfect companion who struggles to become free". Greer's win felt like the right moment to ask New Scientist staff to nominate their own favourite fictional robotic beings, from page or screen. After a bit of quibbling about what constitutes a robot, and a lot of people plumping for various Star Wars droids and Futurama creations, here, in no particular order, they are.

Wegmans is testing AI-powered Caper Carts at four New York locations, allowing shoppers to track spending in real time and skip checkout lines with automatic item detection technology.

At WIRED, we're obsessed with how the world is transforming--and lately, there's been a lot to obsess over. From the breakneck pace of AI research to the tectonic transformation playing out across the US federal government, WIRED's journalists, producers, and editors are committed to reporting from the front lines of these changes and bringing all of you along for the ride. Our goal is to wake up every day and unearth what we describe as "Story Zero": the story before anybody even knows there's a story to tell. We endeavor to do that work in a way that's conversational and accessible, fearless and definitive, and ultimately helps you understand what's changing, why, and how it'll affect your present and your future. I'm incredibly proud that our work this year has often achieved the lofty goals we set for ourselves: WIRED journalists have produced groundbreaking reporting on DOGE's disruption of federal agencies, unearthed ambiguities in the Jeffery Epstein video, delivered a constant drumbeat of clear-eyed coverage on AI's real-world impact (and the AI industry's outrageous talent wars), and found the time to execute on narrative stories that run the gamut, from an AI-inflected murder cult to the quantum apocalypse right around the corner.

A growing number of fire departments across the country are turning to artificial intelligence to help detect and respond to wildfires more quickly. A major breakthrough in artificial intelligence and high-performance computing is on the way, and it's coming from Georgia Tech. Backed by a 20 million investment from the National Science Foundation (NSF), the university is building a supercomputer named Nexus. It's expected go online in spring 2026. Sign up for my FREE CyberGuy Report Get my best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox.

Early large-scale audio datasets, such as LibriSpeech, were built with hundreds of individual contributors whose voices were instrumental in the development of speech technologies, including audiobooks and voice assistants. Y et, a decade later, these same contributions have exposed voice actors to a range of risks. While existing ethical frameworks emphasize Consent, Credit, and Compensation (C), they do not adequately address the emergent risks involving vocal identities that are increasingly decoupled from context, authorship, and control. Drawing on qualitative interviews with 20 professional voice actors, this paper reveals how synthetic replication of voice without clear provenance or enforceable constraints exposes individuals to both reputational and security threats. Beyond reputational harm, such as re-purposing voice data in erotic content, offensive political messaging, and meme culture, we document concerns about accountability breakdowns when their voice is leveraged to clone voices that are deployed in high-stakes scenarios such as financial fraud, misinformation campaigns, or impersonation scams. In such cases, actors face social and legal fallout without recourse, while very few of them have a legal representative or union protection. To make sense of these shifting dynamics, we introduce the PRAC framework - an expansion of C that foregrounds Privacy, Reputation, Accountability, Consent, Credit, and Compensation as interdependent pillars of data used in the synthetic voice economy. This framework captures how privacy risks are amplified through non-consensual training, how reputational harm arises from decontextualized deployment, and how accountability can be reimagined AI Data ecosystems. We argue that voice, as both a biometric identifier and creative labor, demands governance models that restore creator agency, ensure traceability, and establish enforceable boundaries for ethical reuse.

Coordinated online behavior, which spans from beneficial collective actions to harmful manipulation such as disinformation campaigns, has become a key focus in digital ecosystem analysis. Traditional methods often rely on monomodal approaches, focusing on single types of interactions like co-retweets or co-hashtags, or consider multiple modalities independently of each other. However, these approaches may overlook the complex dynamics inherent in multimodal coordination. This study compares different ways of operationalizing the detection of multimodal coordinated behavior. It examines the trade-off between weakly and strongly integrated multimodal models, highlighting the balance between capturing broader coordination patterns and identifying tightly coordinated behavior. By comparing monomodal and multimodal approaches, we assess the unique contributions of different data modalities and explore how varying implementations of multimodality impact detection outcomes. Our findings reveal that not all the modalities provide distinct insights, but that with a multimodal approach we can get a more comprehensive understanding of coordination dynamics. This work enhances the ability to detect and analyze coordinated online behavior, offering new perspectives for safeguarding the integrity of digital platforms.

Can we determine someone's geographic location purely from the sounds they hear? Are acoustic signals enough to localize within a country, state, or even city? We tackle the challenge of global-scale audio geolocation, formalize the problem, and conduct an in-depth analysis with wildlife audio from the iNatSounds dataset. Adopting a vision-inspired approach, we convert audio recordings to spectrograms and benchmark existing image geolocation techniques. We hypothesize that species vocalizations offer strong geolocation cues due to their defined geographic ranges and propose an approach that integrates species range prediction with retrieval-based geolocation. We further evaluate whether geolocation improves when analyzing species-rich recordings or when aggregating across spatiotemporal neighborhoods. Finally, we introduce case studies from movies to explore multimodal geolocation using both audio and visual content. Our work highlights the advantages of integrating audio and visual cues, and sets the stage for future research in audio geolocation.