Multivariate zero-inflated count data arise in a wide range of areas such as economics, social sciences, and biology.

Recent advances in large language models (LLMs) have shown remarkable progress, yet their capacity for logical ``slow-thinking'' reasoning persists as a critical research frontier. Current inference scaling paradigms suffer from two fundamental constraints: fragmented thought flows compromising logical coherence, and intensively computational complexity that escalates with search space dimensions. To overcome these limitations, we present \textbf{Atomic Reasoner} (\textbf{AR}), a cognitive inference strategy that enables fine-grained reasoning through systematic atomic-level operations. AR decomposes the reasoning process into atomic cognitive units, employing a cognitive routing mechanism to dynamically construct reasoning representations and orchestrate inference pathways. This systematic methodology implements stepwise, structured cognition, which ensures logical coherence while significantly reducing cognitive load, effectively simulating the cognitive patterns observed in human deep thinking processes. Extensive experimental results demonstrate AR's superior reasoning capabilities without the computational burden of exhaustive solution searches, particularly excelling in linguistic logic puzzles. These findings substantiate AR's effectiveness in enhancing LLMs' capacity for robust, long-sequence logical reasoning and deliberation.

Studies often aim to reveal how neural representations encode aspects of an observer's environment, such as its contents or structure. These are ``first-order" representations (FORs), because they're ``about" the external world. A less-common target is ``higher-order" representations (HORs), which are ``about" FORs -- their contents, stability, or uncertainty. HORs of uncertainty appear critically involved in adaptive behaviors including learning under uncertainty, influencing learning rates and internal model updating based on environmental feedback. However, HORs about uncertainty are unlikely to be direct ``read-outs" of FOR characteristics, instead reflecting estimation processes which may be lossy, bias-prone, or distortive and which may also incorporate estimates of distributions of uncertainty the observer is likely to experience. While some research has targeted neural representations of ``instantaneously" estimated uncertainty, how the brain represents \textit{distributions} of expected uncertainty remains largely unexplored. Here, we propose a novel reinforcement learning (RL) based generative artificial intelligence (genAI) approach to explore neural representations of uncertainty distributions. We use existing functional magnetic resonance imaging data, where humans learned to `de-noise' their brain states to achieve target neural patterns, to train denoising diffusion genAI models with RL algorithms to learn noise distributions similar to how humans might learn to do the same. We then explore these models' learned noise-distribution HORs compared to control models trained with traditional backpropagation. Results reveal model-dependent differences in noise distribution representations -- with the RL-based model offering much higher explanatory power for human behavior -- offering an exciting path towards using genAI to explore neural noise-distribution HORs.

Robot foundation models hold the potential for deployment across diverse environments, from industrial applications to household tasks. While current research focuses primarily on the policies' generalization capabilities across a variety of tasks, it fails to address safety, a critical requirement for deployment on real-world systems. In this paper, we introduce a safety layer designed to constrain the action space of any generalist policy appropriately. Our approach uses ATACOM, a safe reinforcement learning algorithm that creates a safe action space and, therefore, ensures safe state transitions. By extending ATACOM to generalist policies, our method facilitates their deployment in safety-critical scenarios without requiring any specific safety fine-tuning. We demonstrate the effectiveness of this safety layer in an air hockey environment, where it prevents a puck-hitting agent from colliding with its surroundings, a failure observed in generalist policies.

Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating acceleration effects either explicitly in the model or implicitly through the learning objective. Unlike diffusion models, which rely on a noisy forward process and iterative denoising steps, flow matching trains a continuous transformation (flow) that directly maps a simple prior distribution to the target trajectory distribution without any denoising procedure. By modeling trajectories with second-order dynamics, our approach ensures that generated robot motions are smooth and physically executable, avoiding the jerky or dynamically infeasible trajectories that first-order models might produce. We empirically demonstrate that this second-order conditional flow matching yields superior performance on motion planning benchmarks, achieving smoother trajectories and higher success rates than baseline planners. These findings highlight the advantage of learning acceleration-aware motion fields, as our method outperforms existing motion planning methods in terms of trajectory quality and planning success.

When Netflix first started adding video games to its huge catalogue of streaming TV shows and films, it did so quietly. In 2021, after releasing an impressive experiment with the idea of interactive film in Black Mirror: Bandersnatch in 2018 and a free Stranger Things game in 2019, Netflix began expanding more fully into interactive entertainment. The streamer's gaming offering, for a long time, was its best-kept secret. Whoever was running it really had an eye for quality: award-winningly brilliant and relatively little-known indie games comprised the majority of its catalogue, alongside decent licensed games based on everything from The Queen's Gambit to the reality dating show Too Hot to Handle. Subscribers could play games such as Before Your Eyes, a brief and touching story about a life cut short; Spiritfarer, about guiding lost souls to rest and Into the Breach, a superb sci-fi strategy game with robots v aliens.

Large Language Models (LLMs) have shown remarkable potential in reasoning while they still suffer from severe factual hallucinations due to timeliness, accuracy, and coverage of parametric knowledge. Meanwhile, integrating reasoning with retrieval-augmented generation (RAG) remains challenging due to ineffective task decomposition and redundant retrieval, which can introduce noise and degrade response quality. In this paper, we propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP), enabling strategic and adaptive retrieval. By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step. Experiments show that DeepRAG improves retrieval efficiency while improving answer accuracy by 21.99%, demonstrating its effectiveness in optimizing retrieval-augmented reasoning.

Pope Francis met with top comedians at the Vatican on Friday to encourage them to "spread peace" in the midst of "gloomy" news. A delegation representing the Holy See urged the United Nations this week to put a moratorium on autonomous weapons designed to kill without human decision-making. Archbishop Ettore Balestrero, the Holy See's Permanent Observer to the United Nations in Geneva, gave the warning Monday during an expert session on Emerging Technologies in the Area of Lethal Autonomous Weapons Systems (LAWS). "For the Holy See, autonomous weapons systems cannot be considered as morally responsible entities," Balestrero explained. "The human person, endowed with reason, possesses a unique capacity for moral judgment and ethical decision-making that cannot be replicated by any set of algorithms, no matter how complex." POPE FRANCIS SAYS INTENTIONALLY ALLOWING MIGRANTS TO DIE IS A'GRAVE SIN' The Vatican City flag flies outside the United Nations headquarters in New York City.

Tom Newhouse, vice president of Convergence Media, discusses the potential impact of artificial intelligence on elections after an RNC AI ad garnered attention. EXCLUSIVE: The chairman of the Senate Homeland Security and Governmental Affairs Committee is planning a series of hearings in the coming weeks and months to bring his members up to speed on artificial intelligence, as Congress faces a growing number of calls to regulate the emerging technology. Sen. Gary Peters, D-Mich., told Fox News Digital that the Senate has plenty to learn about AI, and that he has several hearings in mind. "I'm hoping every time we come back here for a work period, that we're going to have a hearing taking a different topic related to AI up, so that we can get just a good sense of where the technology is today, where it's going in the future. What are some of the opportunities that it presents, as well as some of the threats?" the senator explained.

Care and Feeding is Slate's parenting advice column. Have a question for Care and Feeding? This may seem like a low-stakes question, but I am truly concerned. My 15-year-old daughter is an extreme introvert, and strongly dislikes big groups of people and large events. She finds it difficult to make conversation and is seemingly uncomfortable even with talking with some of her classmates, even those she has known for years.