Microgrids have emerged as a pivotal solution in the quest for a sustainable and energy-efficient future. While microgrids offer numerous advantages, they are also prone to issues related to reliably forecasting renewable energy demand and production, protecting against cyberattacks, controlling operational costs, optimizing power flow, and regulating the performance of energy management systems (EMS). Tackling these energy management challenges is essential to facilitate microgrid applications and seamlessly incorporate renewable energy resources. Artificial intelligence (AI) has recently demonstrated immense potential for optimizing energy management in microgrids, providing efficient and reliable solutions. This paper highlights the combined benefits of enabling AI-based methodologies in the energy management systems of microgrids by examining the applicability and efficiency of AI-based EMS in achieving specific technical and economic objectives. The paper also points out several future research directions that promise to spearhead AI-driven EMS, namely the development of self-healing microgrids, integration with blockchain technology, use of Internet of things (IoT), and addressing interpretability, data privacy, scalability, and the prospects to generative AI in the context of future AI-based EMS.

Developing large audio language models (LMs) capable of understanding diverse spoken interactions is essential for accommodating the multimodal nature of human communication and can increase the accessibility of language technologies across different user populations. Recent work on audio LMs has primarily evaluated their performance on short audio segments, typically under 30 seconds, with limited exploration of long-form conversational speech segments that more closely reflect natural user interactions with these models. We introduce Brutally Long Audio Bench (BLAB), a challenging long-form audio benchmark that evaluates audio LMs on localization, duration estimation, emotion, and counting tasks using audio segments averaging 51 minutes in length. BLAB consists of 833+ hours of diverse, full-length audio clips, each paired with human-annotated, text-based natural language questions and answers. Our audio data were collected from permissively licensed sources and underwent a human-assisted filtering process to ensure task compliance. We evaluate six open-source and proprietary audio LMs on BLAB and find that all of them, including advanced models such as Gemini 2.0 Pro and GPT-4o, struggle with the tasks in BLAB. Our comprehensive analysis reveals key insights into the trade-offs between task difficulty and audio duration. In general, we find that audio LMs struggle with long-form speech, with performance declining as duration increases. They perform poorly on localization, temporal reasoning, counting, and struggle to understand non-phonemic information, relying more on prompts than audio content. BLAB serves as a challenging evaluation framework to develop audio LMs with robust long-form audio understanding capabilities.

Estimating physical parameters from data is a crucial application of machine learning (ML) in the physical sciences. However, systematic uncertainties, such as detector miscalibration, induce data distribution distortions that can erode statistical precision. In both high-energy physics (HEP) and broader ML contexts, achieving uncertainty-aware parameter estimation under these domain shifts remains an open problem. In this work, we address this challenge of uncertainty-aware parameter estimation for a broad set of tasks critical for HEP. We introduce a novel approach based on Contrastive Normalizing Flows (CNFs), which achieves top performance on the HiggsML Uncertainty Challenge dataset. Building on the insight that a binary classifier can approximate the model parameter likelihood ratio, we address the practical limitations of expressivity and the high cost of simulating high-dimensional parameter grids by embedding data and parameters in a learned CNF mapping. This mapping yields a tunable contrastive distribution that enables robust classification under shifted data distributions. Through a combination of theoretical analysis and empirical evaluations, we demonstrate that CNFs, when coupled with a classifier and established frequentist techniques, provide principled parameter estimation and uncertainty quantification through classification that is robust to data distribution distortions.

Federated Learning (FL) enables distributed machine learning training while preserving privacy, representing a paradigm shift for data-sensitive and decentralized environments. Despite its rapid advancements, FL remains a complex and multifaceted field, requiring a structured understanding of its methodologies, challenges, and applications. In this survey, we introduce a meta-framework perspective, conceptualising FL as a composition of modular components that systematically address core aspects such as communication, optimisation, security, and privacy. We provide a historical contextualisation of FL, tracing its evolution from distributed optimisation to modern distributed learning paradigms. Additionally, we propose a novel taxonomy distinguishing Aggregation from Alignment, introducing the concept of alignment as a fundamental operator alongside aggregation. To bridge theory with practice, we explore available FL frameworks in Python, facilitating real-world implementation. Finally, we systematise key challenges across FL sub-fields, providing insights into open research questions throughout the meta-framework modules. By structuring FL within a meta-framework of modular components and emphasising the dual role of Aggregation and Alignment, this survey provides a holistic and adaptable foundation for understanding and advancing FL research and deployment.

Recent legal frameworks have mandated the right to be forgotten, obligating the removal of specific data upon user requests. Machine Unlearning has emerged as a promising solution by selectively removing learned information from machine learning models. This paper presents MUBox, a comprehensive platform designed to evaluate unlearning methods in deep learning. MUBox integrates 23 advanced unlearning techniques, tested across six practical scenarios with 11 diverse evaluation metrics. It allows researchers and practitioners to (1) assess and compare the effectiveness of different machine unlearning methods across various scenarios; (2) examine the impact of current evaluation metrics on unlearning performance; and (3) conduct detailed comparative studies on machine unlearning in a unified framework. Leveraging MUBox, we systematically evaluate these unlearning methods in deep learning and uncover several key insights: (a) Even state-of-the-art unlearning methods, including those published in top-tier venues and winners of unlearning competitions, demonstrate inconsistent effectiveness across diverse scenarios. Prior research has predominantly focused on simplified settings, such as random forgetting and class-wise unlearning, highlighting the need for broader evaluations across more difficult unlearning tasks. (b) Assessing unlearning performance remains a non-trivial problem, as no single evaluation metric can comprehensively capture the effectiveness, efficiency, and preservation of model utility. Our findings emphasize the necessity of employing multiple metrics to achieve a balanced and holistic assessment of unlearning methods. (c) In the context of depoisoning, our evaluation reveals significant variability in the effectiveness of existing approaches, which is highly dependent on the specific type of poisoning attacks.

Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data engineering techniques, such as representing age with a histogram or encoding race in a specific way, can manipulate feature importance as determined by popular methods like SHAP. Notably, the sensitivity of explanations to feature representation can be exploited by adversaries to obscure issues like discrimination. While the intuition behind these results is straightforward, their systematic exploration has been lacking. Previous work has focused on adversarial attacks on feature-based explainers by biasing data or manipulating models. To the best of our knowledge, this is the first study demonstrating that explainers can be misled by standard, seemingly innocuous data engineering techniques.

Machine unlearning methods take a model trained on a dataset and a forget set, then attempt to produce a model as if it had only been trained on the examples not in the forget set. We empirically show that an adversary is able to distinguish between a mirror model (a control model produced by retraining without the data to forget) and a model produced by an unlearning method across representative unlearning methods from the literature. We build distinguishing algorithms based on evaluation scores in the literature (i.e. membership inference scores) and Kullback-Leibler divergence. We propose a strong formal definition for machine unlearning called computational unlearning. Computational unlearning is defined as the inability for an adversary to distinguish between a mirror model and a model produced by an unlearning method. If the adversary cannot guess better than random (except with negligible probability), then we say that an unlearning method achieves computational unlearning. Our computational unlearning definition provides theoretical structure to prove unlearning feasibility results. For example, our computational unlearning definition immediately implies that there are no deterministic computational unlearning methods for entropic learning algorithms. We also explore the relationship between differential privacy (DP)-based unlearning methods and computational unlearning, showing that DP-based approaches can satisfy computational unlearning at the cost of an extreme utility collapse. These results demonstrate that current methodology in the literature fundamentally falls short of achieving computational unlearning. We conclude by identifying several open questions for future work.

An AI tool has been used to review public responses to a government consultation for the first time and is now set to be rolled out more widely in an effort to save money and staff time. The tool, named "Consult", was first used by the Scottish government when it was seeking perspectives on the regulation of non-surgical cosmetic procedures such as lip filler. The UK government said the tool analysed responses and was able to produce results identical to human officials, and will now be used to review responses from other consultations, while also being developed further. While reviewing more than 2,000 responses, Consult identified key themes, which were then checked and refined by experts in the Scottish government. The government built Consult to be among its new package of AI tools, nicknamed "Humphrey", which they claim will "speed up work in Whitehall and cut back on consulting spending".

On a Wednesday morning last month, I thought, just for a second, that AI was going to kill me. I had hailed a self-driving Waymo to bring me to a hacker house in Nob Hill, San Francisco. Just a few blocks from arrival, the car lurched toward the other lane--which was, thankfully, empty--and immediately jerked back. That sense of peril felt right for the moment. As I stepped into the cab, Federal Reserve Chair Jerome Powell was delivering a speech criticizing President Donald Trump's economic policies, and in particular the administration's sweeping on-again, off-again tariffs. A day earlier, the White House had claimed that Chinese goods would be subject to overall levies as high as 245 percent when accounting for preexisting tariffs, and the AI giant Nvidia's stock had plummeted after the company reported that it expected to take a quarterly hit of more than 5 billion for selling to China.

Raul Gastesi speaks with Fox News Digital about a bill moving through the Florida Senate that would give homeowners the right to use "reasonable force" to take down drones infringing on their privacy rights. A newly-minted law allowing Arizona law enforcement officers to shoot down drug-carrying drones along the U.S.-Mexico border has taken effect after sailing through the state's legislature with bipartisan support. HB 2733 was signed into law on April 18 and grants officers the ability to target drones suspected of carrying out illegal activity within 15 miles of the state's international border. "Cartels are increasingly using drones to survey the border to locate [U.S. Customs and Border Protection] officers' locations and to transport illegal drugs from Mexico into our state," state Rep. David Marshall, the bill's sponsor, said in a statement to Fox News Digital. "Law enforcement tools at [our] disposal will be electronic jamming devices, as well as using shotguns with bird shot to bring down these drones."