--Evolving fuzzy systems build and adapt fuzzy models--such as predictors and controllers--by incrementally updating their rule-base structure from data streams. On the occasion of the 60-year anniversary of fuzzy set theory, commemorated during the Fuzz-IEEE 2025 event, this brief paper revisits the historical development and core contributions of classical fuzzy and adaptive modeling and control frameworks. It then highlights the emergence and significance of evolving intelligent systems in fuzzy modeling and control, emphasizing their advantages in handling nonstationary environments. Key challenges and future directions are discussed, including safety, interpretability, and principled structural evolution. Research in fuzzy modeling, control, and applications has grown rapidly since Zadeh's seminal work in 1965 [1], evolving into a vast and multifaceted field.

We introduce TimeMCL, a method leveraging the Multiple Choice Learning (MCL) paradigm to forecast multiple plausible time series futures. Our approach employs a neural network with multiple heads and utilizes the Winner-Takes-All (WTA) loss to promote diversity among predictions. MCL has recently gained attention due to its simplicity and ability to address ill-posed and ambiguous tasks. We propose an adaptation of this framework for time-series forecasting, presenting it as an efficient method to predict diverse futures, which we relate to its implicit quantization objective. We provide insights into our approach using synthetic data and evaluate it on real-world time series, demonstrating its promising performance at a light computational cost.

We introduce kernel density machines (KDM), a nonparametric estimator of a Radon--Nikodym derivative, based on reproducing kernel Hilbert spaces. KDM applies to general probability measures on countably generated measurable spaces under minimal assumptions. For computational efficiency, we incorporate a low-rank approximation with precisely controlled error that grants scalability to large-sample settings. We provide rigorous theoretical guarantees, including asymptotic consistency, a functional central limit theorem, and finite-sample error bounds, establishing a strong foundation for practical use. Empirical results based on simulated and real data demonstrate the efficacy and precision of KDM.

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal paradigm, providing the rich toolbox of causality to identify the persistent challenges, such as causal misidentification, preference heterogeneity, and confounding due to user-specific factors. Inheriting from the literature of causal inference, we identify key assumptions necessary for reliable generalisation and contrast them with common data collection practices. We illustrate failure modes of naive reward models and demonstrate how causally-inspired approaches can improve model robustness. Finally, we outline desiderata for future research and practices, advocating targeted interventions to address inherent limitations of observational data.

Patient stratification--identifying clinically meaningful subgroups--is essential for advancing personalized medicine through improved diagnostics and treatment strategies. Electronic health records (EHRs), particularly those from intensive care units (ICUs), contain rich temporal clinical data that can be leveraged for this purpose. In this work, we introduce ICU-TSB (Temporal Stratification Benchmark), the first comprehensive benchmark for evaluating patient stratification based on temporal patient representation learning using three publicly available ICU EHR datasets. A key contribution of our benchmark is a novel hierarchical evaluation framework utilizing disease taxonomies to measure the alignment of discovered clusters with clinically validated disease groupings. In our experiments with ICU-TSB, we compared statistical methods and several recurrent neural networks, including LSTM and GRU, for their ability to generate effective patient representations for subsequent clustering of patient trajectories. Our results demonstrate that temporal representation learning can rediscover clinically meaningful patient cohorts; nevertheless, it remains a challenging task, with v-measuring varying from up to 0.46 at the top level of the taxonomy to up to 0.40 at the lowest level. To further enhance the practical utility of our findings, we also evaluate multiple strategies for assigning interpretable labels to the identified clusters.

Neural networks are computational models that aim to generalize patterns found in datasets from which they are determined by means of a learning algorithm [8]. Despite the undeniable advancement in the state of the art of intelligent systems promoted by neural networks, their lack of interpretability is subject to criticism. Neural networks suffer from the black box problem due to the lack of justification for their results and the impossibility to directly inspect their learned information [3, 5]. As several architectures of neural networks realize piecewise linear functions or may be approximated by them, a path towards interpretability is through regional format representations of such neural networks and functions by explicit sets of pairs p, Ω of a linear piece p and a region Ω such that, for a vector of input values x Ω, the output is given by p(x). An algorithm for establishing regional representations from feedforward neural networks with rectified linear units as activation functions is proposed in [15]. The main goal of this work is to introduce an algorithm for computing regional format representations of ReLU-TId neural networks, which are feedforward neural networks with rectified linear units as activation functions in hidden layers and truncated identity as activation functions in the output layer.

While gender bias in large language models (LLMs) has been extensively studied in many domains, uses of LLMs in e-commerce remain largely unexamined and may reveal novel forms of algorithmic bias and harm. Our work investigates this space, developing data-driven taxonomic categories of gender bias in the context of product description generation, which we situate with respect to existing general purpose harms taxonomies. We illustrate how AI-generated product descriptions can uniquely surface gender biases in ways that require specialized detection and mitigation approaches. Further, we quantitatively analyze issues corresponding to our taxonomic categories in two models used for this task -- GPT-3.5 and an e-commerce-specific LLM -- demonstrating that these forms of bias commonly occur in practice. Our results illuminate unique, under-explored dimensions of gender bias, such as assumptions about clothing size, stereotypical bias in which features of a product are advertised, and differences in the use of persuasive language. These insights contribute to our understanding of three types of AI harms identified by current frameworks: exclusionary norms, stereotyping, and performance disparities, particularly for the context of e-commerce.

Biggest drone strike yet on Ukraine's second city 24 minutes agoShareSaveJaroslav LukivBBC NewsShareSaveKharkiv Regional AdministrationUkraine's emergencies workers search for survivors at one of Kharkiv's damaged residential buildings At least two people have been killed and another 17 injured in the biggest Russian drone attack on Ukraine's second-largest city of Kharkiv, the mayor says. Ihor Terekhov says that overnight Russia launched 48 drones, as well as two missiles and four gliding bombs. "We have a lot of damage," he says, adding that three high-rising residential buildings were hit. Footage has emerged showing several storeys of one such building on fire. Six people were killed and 80 injured across Ukraine the previous night, when Russia attacked the country with more than 400 drones and nearly 40 missiles.

The United Nations' digital agency says that operational carbon emissions for the world's top tech companies rose an average of 150 percent between 2020 and 2023 as investments in artificial intelligence (AI) and data centres drove up global electricity demand. Operational emissions for Amazon grew 182 percent in 2023 against 2020 levels, while emissions for Microsoft grew 155 percent, Facebook and Instagram owner Meta grew 145 percent, and Google parent company Alphabet grew 138 percent over the same period, according to the UN's International Telecommunication Union (ITU). The figures include the emissions directly created by the companies' operations as well as those from purchased energy consumption. They were included in a new report from ITU assessing the greenhouse gas emissions of the world's top 200 digital companies between 2020 and 2023. The UN agency linked the sharp uptick to recent breakthroughs in AI and the demand for digital services like cloud computing.

Quantified Integer Programming (QIP) bridges multiple domains by extending Quantified Boolean Formulas (QBF) to incorporate general integer variables and linear constraints while also generalizing Integer Programming through variable quantification. As a special case of Quantified Constraint Satisfaction Problems (QCSP), QIP provides a versatile framework for addressing complex decision-making scenarios. Additionally, the inclusion of a linear objective function enables QIP to effectively model multistage robust discrete linear optimization problems, making it a powerful tool for tackling uncertainty in optimization. While two primary solution paradigms exist for QBF -- search-based and expansion-based approaches -- only search-based methods have been explored for QIP and QCSP. We introduce an expansion-based approach for QIP using Counterexample-Guided Abstraction Refinement (CEGAR), adapting techniques from QBF. We extend this methodology to tackle multistage robust discrete optimization problems with linear constraints and further embed it in an optimization framework, enhancing its applicability. Our experimental results highlight the advantages of this approach, demonstrating superior performance over existing search-based solvers for QIP in specific instances. Furthermore, the ability to model problems using linear constraints enables notable performance gains over state-of-the-art expansion-based solvers for QBF.