Did a Chatbot Write a Prize-Winning Story? If the possibility that one or more of the winners of the Commonwealth Short Story Prize was A.I.-generated chills us, it may be because of what it reveals about human writing. In early May, the Commonwealth Foundation announced the five regional winners for its influential Short Story Prize, which recognizes unpublished short fiction. One of the awardees, a Trinidadian writer named Jamir Nazir, was accused of A.I.-assisted cheating by a broad array of social-media users who seized upon his story's synthetic tics, glitchy metaphors, and general unreadability. "Maybe it was a name; maybe rain took a shape and decided to keep it.")

Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability across diverse tasks, while demonstration-based methods struggle to generalize beyond their training distribution. We introduce GROVE, a generalized reward framework that enables open-vocabulary physical skill learning without manual engineering or task-specific demonstrations. Our key insight is that Large Language Models(LLMs) and Vision Language Models(VLMs) provide complementary guidance -- LLMs generate precise physical constraints capturing task requirements, while VLMs evaluate motion semantics and naturalness. Through an iterative design process, VLM-based feedback continuously refines LLM-generated constraints, creating a self-improving reward system. To bridge the domain gap between simulation and natural images, we develop Pose2CLIP, a lightweight mapper that efficiently projects agent poses directly into semantic feature space without computationally expensive rendering. Extensive experiments across diverse embodiments and learning paradigms demonstrate GROVE's effectiveness, achieving 22.2% higher motion naturalness and 25.7% better task completion scores while training 8.4x faster than previous methods. These results establish a new foundation for scalable physical skill acquisition in simulated environments.

Vision-Language Models (VLMs) learn joint representations by mapping images and text into a shared latent space. However, recent research highlights that deterministic embeddings from standard VLMs often struggle to capture the uncertainties arising from the ambiguities in visual and textual descriptions and the multiple possible correspondences between images and texts. Existing approaches tackle this by learning probabilistic embeddings during VLM training, which demands large datasets and does not leverage the powerful representations already learned by large-scale VLMs like CLIP. In this paper, we propose GroVE, a post-hoc approach to obtaining probabilistic embeddings from frozen VLMs. GroVE builds on Gaussian Process Latent Variable Model (GPLVM) to learn a shared low-dimensional latent space where image and text inputs are mapped to a unified representation, optimized through single-modal embedding reconstruction and cross-modal alignment objectives. Once trained, the Gaussian Process model generates uncertainty-aware probabilistic embeddings. Evaluation shows that GroVE achieves state-of-the-art uncertainty calibration across multiple downstream tasks, including cross-modal retrieval, visual question answering, and active learning.

Election day is here and so too is the anxiety that has parked itself in the middle of the room. Some people are trying their best to meet the moment -- with mixed results -- while others have simply chosen not to let the race for president and control of Congress dominate their lives. For most all of the voters we spoke to, it's easier said than done. They planned to go for a hike and visit art galleries around downtown L.A. but admitted they were stressed about the election. "We're just sort of out walking around and trying to have a pleasant day and not think about it too much," Mark "I think we'll be glued to our TVs tonight to find out how the rest of our lives are gonna go."

Conditional story generation is significant in human-machine interaction, particularly in producing stories with complex plots. While Large language models (LLMs) perform well on multiple NLP tasks, including story generation, it is challenging to generate stories with both complex and creative plots. Existing methods often rely on detailed prompts to guide LLMs to meet target conditions, which inadvertently restrict the creative potential of the generated stories. We argue that leveraging information from exemplary human-written stories facilitates generating more diverse plotlines. Delving deeper into story details helps build complex and credible plots. In this paper, we propose a retrieval-au\textbf{G}mented sto\textbf{R}y generation framework with a f\textbf{O}rest of e\textbf{V}id\textbf{E}nce (GROVE) to enhance stories' complexity. We build a retrieval repository for target conditions to produce few-shot examples to prompt LLMs. Additionally, we design an ``asking-why'' prompting scheme that extracts a forest of evidence, providing compensation for the ambiguities that may occur in the generated story. This iterative process uncovers underlying story backgrounds. Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility. Experimental results and numerous examples verify the effectiveness of our method.

Intel Corp co-founder Gordon Moore, a pioneer in the semiconductor industry whose "Moore's Law" predicted a steady rise in computing power for decades, has died at the age of 94, the company announced. Intel and Moore's family philanthropic foundation said he died on Friday surrounded by family at his home in Hawaii. Co-launching Intel in 1968, Moore was the rolled-up-sleeves engineer within a triumvirate of technology luminaries that eventually put "Intel Inside" processors in more than 80% of the world's personal computers. In an article he wrote in 1965, Moore observed that, thanks to improvements in technology, the number of transistors on microchips had roughly doubled every year since integrated circuits were invented a few years before. His prediction that the trend would continue became known as "Moore's Law" and, later amended to every two years, it helped push Intel and rival chipmakers to aggressively target their research and development resources to make sure that rule of thumb came true.

Hidden Markov Models have been used frequently in the audio domain to identify underlying musical structure. Much less work has been done in the purely symbolic realm. Recently, a substantial amount of expert-labelled symbolic musical data has been injected into the research community. The new availability of data allows for the application of machine learning models to purely symbolic tasks. Similarly, the continued expansion of the field of machine learning provides new perspectives and implementations of machine learning methods, which are powerful tools when approaching complex musical challenges. This research explores the use of an extended probabilistic model such as the Hidden Semi-Markov Model (HSMM) to approach the task of automatic harmonization. One distinct advantage of the HSMM is that it is able to automatically differentiate harmonic boundaries, through its inclusion of an extra parameter: duration. In this way, a melody can be harmonized automatically in the style of a particular corpus. In the case of this research, the corpus was in the style of Rock'n' Roll.

WALMART is a giant retail organization that managed to keep up with its customer's changing needs in the digital era, delivering groceries and everyday essentials as efficiently as delivering on expectations. At a recent conference, Business Insider heard Walmart Chief Digital Officer Bill Groves talk about the organization's journey to digital. Groves revealed that Walmart employs roughly 1,500 data scientists and 50,000 software engineers who support the 100,000-odd artificial intelligence (AI) and machine learning (ML) projects that the organization currently runs. "I do more work in the AI and [machine learning] space then I have ever done in my life. We're involved in robotics, we're involved in micro-personalization, we're involved in probably the biggest supply chain in the world." The important thing, however, is that Groves said that Walmart's success rate with AI and ML projects is 75 percent.

Walmart is a leader in the push to adopt artificial intelligence and machine learning. Still, the world's largest retailer runs into many of the problems other organizations experience when pursuing the advanced technology. The company currently employs roughly 1,500 data scientists and 50,000 software engineers throughout the enterprise, according to chief data officer Bill Groves, who directly oversees a smaller staff of 100 tech workers. A Walmart spokesperson did not respond to a request to confirm those numbers. Those employees help support the over 100,000 different machine learning or AI-based projects the organization currently has in production.

A team of unmanned aerial vehicle experts led by the University of Alaska Fairbanks is working on delivering emergency medical supplies and, maybe later, cargo across Alaska with drones. UAF recently announced an upcoming test to fly a package across Turnagain Arm from Indian to Hope, and while that package -- a three-pound box of Q-tips, actually -- is only one step toward those goals, it could eventually lead to major changes for Alaska communities off the road system. Cathy Cahill, director of the Alaska Center for Unmanned Aircraft Systems Integration, spoke with Alaska Public Media's Casey Grove about the test and the center's work. Grove: Alaska has this kind of amazing history of delivering medical supplies in emergencies, you know, 1925, dog mushers running diphtheria serum to Nome, that kind of thing. So this idea seems kind of obvious, and not to be rude, but drones have been around for a while, why aren't we already doing this?