Turn-taking is a fundamental aspect of conversation, but current Human-Robot Interaction (HRI) systems often rely on simplistic, silence-based models, leading to unnatural pauses and interruptions. This paper investigates, for the first time, the application of general turn-taking models, specifically TurnGPT and Voice Activity Projection (VAP), to improve conversational dynamics in HRI. These models are trained on human-human dialogue data using self-supervised learning objectives, without requiring domain-specific fine-tuning. We propose methods for using these models in tandem to predict when a robot should begin preparing responses, take turns, and handle potential interruptions. We evaluated the proposed system in a within-subject study against a traditional baseline system, using the Furhat robot with 39 adults in a conversational setting, in combination with a large language model for autonomous response generation. The results show that participants significantly prefer the proposed system, and it significantly reduces response delays and interruptions.

Recently there have been many shared tasks targeting the detection of generated text from Large Language Models (LLMs). However, these shared tasks tend to focus either on cases where text is limited to one particular domain or cases where text can be from many domains, some of which may not be seen during test time. In this shared task, using the newly released RAID benchmark, we aim to answer whether or not models can detect generated text from a large, yet fixed, number of domains and LLMs, all of which are seen during training. Over the course of three months, our task was attempted by 9 teams with 23 detector submissions. We find that multiple participants were able to obtain accuracies of over 99% on machine-generated text from RAID while maintaining a 5% False Positive Rate -- suggesting that detectors are able to robustly detect text from many domains and models simultaneously. We discuss potential interpretations of this result and provide directions for future research.

Taylor Sheridan, the most overextended man in television, has done it again. Landman, according to the internal metrics at Paramount, is the most watched original show the streamer has ever had. Remember, Yellowstone proper is on Peacock.) The West Texas–set story, which stars Billy Bob Thornton as Tommy Norris, an all-purpose problem solver for a fictional oil company owned by Monty Miller (Jon Hamm), has also developed a bit more of a critical halo than Sheridan's other TV ventures, popping up on best-of-2024 lists, edging into mainstream discourse via podcasts that typically cover more-prestige fare, and retaining a score of 80 percent on Rotten Tomatoes. And the week before Landman wrapped up, this past Sunday night, its lead actor, Billy Bob Thornton, attended the Golden Globes as a nominee for his role in the series.

Jeffrey and Cheryll Ku shared a video recorded on their Ring doorbell showing the terrifying moment the Eaton Fire approached their home. Altadena residents Jeffrey and Cheryll Ku shared harrowing footage of their Jan. The Kus are among Los Angeles residents forced to flee from the wildfires that tore through the city. On social media, the Kus described the experience as "34 minutes of pure terror." "The Eaton fire had just started in the hillside above us and we had to act FAST," Jeffrey Ku wrote in an Instagram post.

Kate Mosse and Richard Osman have hit back at Labour's plan to give artificial intelligence companies broad freedoms to mine artistic works for data, saying it could destroy growth in creative fields and amount to theft. It is seen as a way of supercharging the growth of AI companies in the UK. Last month Paul McCartney warned that AI "could just take over", and Kate Bush joined Stephen Fry and Hugh Bonneville in signing a petition warning that the "unlicensed use of creative works for training generative AI is a major, unjust threat to the livelihoods of the people behind those works, and must not be permitted". Mosse told the Guardian: "Using AI responsibly and well and being a world leader – all of this I agree with. It just cannot be at the expense of the creative industries … It is supporting one type of growth and destroying another part of growth. And it cannot be on the basis of theft of our work."

Fox News' senior national correspondent William La Jeunesse joins'America's Newsroom' to discuss Congress' history of killing pushes for cost-cutting. FIRST ON FOX: The Congressional Department of Government Efficiency (DOGE) Caucus is holding its second-ever meeting on Wednesday, where its leaders are expected to unveil a set of "principles" to guide the group in its mission to cut government waste. They outlined eight goals, some practical while others more symbolic, in a bid to ensure the caucus is in sync with the DOGE advisory panel set up by President-elect Donald Trump. "The federal government must serve the interests of taxpayers, and taxpayers are best served by a lean, efficient, transparent, and accountable bureaucracy," the first principle read, according to a draft memo obtained by Fox News Digital. The document also suggested both lofty and smaller-scale goals.

From a daily skincare routine to Botox and face lifts, some people will do almost anything to turn back the hands of time. Now, some actors are going one step further and using a controversial technology to digitally'de-age' their appearance. In his latest film, Tom Hanks, 68, and his Forrest Gump co-star Robin Wright, 58, use AI to play the same couple at different stages in their lives. Hanks says: 'It's a great tool, because the super computing means you do not have to wait for post-production to do the purely technical visual view of it.' There has been growing concern over the use of AI in cinema, with many actors worrying that the technology will force humans out of the film industry.

Google is being investigated by the UK competition watchdog over the impact of its search and advertising practices on consumers, news publishers, businesses and rival search engines. The CMA estimates that search advertising costs the equivalent of nearly 500 for each UK household a year, which could be kept down with effective competition. The watchdog announced on Tuesday it will investigate if Google is blocking competitors from entering the market, and whether it is engaging in "potential exploitative conduct" by the mass collection of consumers' data without informed consent. It will also investigate whether Google is using its position as the pre-eminent search engine to give an unfair advantage to its own shopping and travel services. The investigation will take up to nine months and could result in Google being forced to share the mountains of data it collects with other businesses, or to give publishers greater control over how their content – books, newspaper articles and music – is used, including by Google's fast-growing artificial intelligence systems.

Generative adversarial networks (GANs) have recently found applications in image editing. However, most GAN-based image editing methods often require large-scale datasets with semantic segmentation annotations for training, only provide high-level control, or merely interpolate between different images. Here, we propose EditGAN, a novel method for high-quality, high-precision semantic image editing, allowing users to edit images by modifying their highly detailed part segmentation masks, e.g., drawing a new mask for the headlight of a car. EditGAN builds on a GAN framework that jointly models images and their semantic segmentation, requiring only a handful of labeled examples – making it a scalable tool for editing. Specifically, we embed an image into the GAN's latent space and perform conditional latent code optimization according to the segmentation edit, which effectively also modifies the image.

Despite their impressive ability to generate high-quality and fluent text, generative large language models (LLMs) also produce hallucinations: statements that are misaligned with established world knowledge or provided input context. However, measuring hallucination can be challenging, as having humans verify model generations on-the-fly is both expensive and time-consuming. In this work, we release HALoGEN, a comprehensive hallucination benchmark consisting of: (1) 10,923 prompts for generative models spanning nine domains including programming, scientific attribution, and summarization, and (2) automatic high-precision verifiers for each use case that decompose LLM generations into atomic units, and verify each unit against a high-quality knowledge source. We use this framework to evaluate ~150,000 generations from 14 language models, finding that even the best-performing models are riddled with hallucinations (sometimes up to 86% of generated atomic facts depending on the domain). We further define a novel error classification for LLM hallucinations based on whether they likely stem from incorrect recollection of training data (Type A errors), or incorrect knowledge in training data (Type B errors), or are fabrication (Type C errors). We hope our framework provides a foundation to enable the principled study of why generative models hallucinate, and advances the development of trustworthy large language models.