We explore an ASR-free method for isolated word reading assessment in low-resource settings. Our few-shot approach compares input child speech to a small set of adult-provided reference templates. Inputs and templates are encoded using intermediate layers from large self-supervised learned (SSL) models. Using an Afrikaans child speech benchmark, we investigate design options such as discretising SSL features and barycentre averaging of the templates. Idealised experiments show reasonable performance for adults, but a substantial drop for child speech input, even with child templates. Despite the success of employing SSL representations in low-resource speech tasks, our work highlights the limitations of SSL representations for processing child data when used in a few-shot classification system.

Semantic segmentation of satellite imagery is crucial for Earth observation applications, but remains constrained by limited labelled training data. While self-supervised pretraining methods like Masked Autoencoders (MAE) have shown promise, they focus on reconstruction rather than localisation-a fundamental aspect of segmentation tasks. We propose adapting LOCA (Location-aware), a position prediction self-supervised learning method, for multimodal satellite imagery semantic segmentation. Our approach addresses the unique challenges of satellite data by extending SatMAE's channel grouping from multispectral to multimodal data, enabling effective handling of multiple modalities, and introducing same-group attention masking to encourage cross-modal interaction during pretraining. The method uses relative patch position prediction, encouraging spatial reasoning for localisation rather than reconstruction. We evaluate our approach on the Sen1Floods11 flood mapping dataset, where it significantly outperforms existing reconstruction-based self-supervised learning methods for satellite imagery. Our results demonstrate that position prediction tasks, when properly adapted for multimodal satellite imagery, learn representations more effective for satellite image semantic segmentation than reconstruction-based approaches.

Feedback is New Scientist's popular sideways look at the latest science and technology news. You can submit items you believe may amuse readers to Feedback by emailing feedback@newscientist.com Feedback has been dimly aware for a while that there is a slew of AI-generated music swamping platforms like Spotify. Our awareness was limited, we confess, because we are so old that we still prefer to listen to CDs. Still, we weren't too surprised when New Scientist's Timothy Revell told us about an indie rock band called The Velvet Sundown that appears to be entirely AI-generated, from their songs, which sound like the beige love-children of Coldplay and the Eagles, to their uncanny-valley Instagram photos, which look like rejected concept art from Daisy Jones & the Six.

Tensor Network (TN) Kernel Machines speed up model learning by representing parameters as low-rank TNs, reducing computation and memory use. However, most TN-based Kernel methods are deterministic and ignore parameter uncertainty. Further, they require manual tuning of model complexity hyperparameters like tensor rank and feature dimensions, often through trial-and-error or computationally costly methods like cross-validation. We propose Bayesian Tensor Network Kernel Machines, a fully probabilistic framework that uses sparsity-inducing hierarchical priors on TN factors to automatically infer model complexity. This enables automatic inference of tensor rank and feature dimensions, while also identifying the most relevant features for prediction, thereby enhancing model interpretability. All the model parameters and hyperparameters are treated as latent variables with corresponding priors. Given the Bayesian approach and latent variable dependencies, we apply a mean-field variational inference to approximate their posteriors. We show that applying a mean-field approximation to TN factors yields a Bayesian ALS algorithm with the same computational complexity as its deterministic counterpart, enabling uncertainty quantification at no extra computational cost. Experiments on synthetic and real-world datasets demonstrate the superior performance of our model in prediction accuracy, uncertainty quantification, interpretability, and scalability.

--Finite-State Machines (FSMs) are critical for modeling the operational logic of network protocols, enabling verification, analysis, and vulnerability discovery. However, existing FSM extraction techniques face limitations such as scalability, incomplete coverage, and ambiguity in natural language specifications. In this paper, we propose FlowFSM, a novel agen-tic framework that leverages Large Language Models (LLMs) combined with prompt chaining and chain-of-thought reasoning to extract accurate FSMs from raw RFC documents. FlowFSM systematically processes protocol specifications, identifies state transitions, and constructs structured rule-books by chaining agent outputs. Experimental evaluation across FTP and RTSP protocols demonstrates that FlowFSM achieves high extraction precision while minimizing hallucinated transitions, showing promising results. Our findings highlight the potential of agent-based LLM systems in the advancement of protocol analysis and FSM inference for cybersecurity and reverse engineering applications.

In this paper, we explore how large language models (LLMs) approach financial decision - making by systematically comparing their responses to those of human participants across the globe. We posed a set of commonly used financial decision - making questions t o seven leading LLMs, including five models from the GPT series (GPT - 4o, GPT - 4.5, o1, o3 - mini), Gemini 2.0 Flash, and DeepSeek R1 . We then compared their outputs to human responses drawn from a dataset covering 53 nations. Our analysis reveals three main r esults. First, LLMs generally exhibit a risk - neutral decision - making pattern, favoring choices aligned with expected value calculations when faced with lottery - type questions . Second, when evaluating trade - offs between present and future, LLMs occasionally produce responses that appear inconsistent with normative reasoning . Third, when we examine cross - national similarities, we f ind that the LLMs' aggregate responses most closely resemble those of participants from Tanzania. These findings contribute to the understanding of how LLMs emulate human - like decision behaviors and highlight potential cultural and training influences embedded within their outputs.

Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages, largely due to limited exposure to these languages during pre-training. A common strategy to address this is to introduce new tokens specific to the target languages, initialize their embeddings, and apply continual pre-training on target-language data. Among such methods, OFA (Liu et al., 2024a) proposes a similarity-based subword embedding initialization heuristic that is both effective and efficient. However, OFA restricts target-language token embeddings to be convex combinations of a fixed number of source-language embeddings, which may limit expressiveness. To overcome this limitation, we propose HYPEROFA, a hypernetwork-based approach for more adaptive token embedding initialization. The hypernetwork is trained to map from an external multilingual word vector space to the PLMs token embedding space using source-language tokens. Once trained, it can generate flexible embeddings for target-language tokens, serving as a good starting point for continual pretraining. Experiments demonstrate that HYPEROFA consistently outperforms random initialization baseline and matches or exceeds the performance of OFA in both continual pre-training convergence and downstream task performance. We make the code publicly available.

As archives turn to artificial intelligence to manage growing volumes of digital records, privacy risks inherent in current AI data practices raise critical concerns about data sovereignty and ethical accountability. This paper explores how privacy-enhancing technologies (PETs) and Web3 architectures can support archives to preserve control over sensitive content while still being able to make it available for access by researchers. We present Clio-X, a decentralized, privacy-first Web3 digital solution designed to embed PETs into archival workflows and support AI-enabled reference and access. Drawing on a user evaluation of a medium-fidelity prototype, the study reveals both interest in the potential of the solution and significant barriers to adoption related to trust, system opacity, economic concerns, and governance. Using Rogers' Diffusion of Innovation theory, we analyze the sociotechnical dimensions of these barriers and propose a path forward centered on participatory design and decentralized governance through a Clio-X Decentralized Autonomous Organization. By integrating technical safeguards with community-based oversight, Clio-X offers a novel model to ethically deploy AI in cultural heritage contexts.

Accurate forecasting of energy demand and supply is critical for optimizing sustainable energy systems, yet it is challenged by the variability of renewable sources and dynamic consumption patterns. This paper introduces a neural framework that integrates continuous-time Neural Ordinary Differential Equations (Neural ODEs), graph attention, multi-resolution wavelet transformations, and adaptive learning of frequencies to address the issues of time series prediction. The model employs a robust ODE solver, using the Runge-Kutta method, paired with graph-based attention and residual connections to better understand both structural and temporal patterns. Through wavelet-based feature extraction and adaptive frequency modulation, it adeptly captures and models diverse, multi-scale temporal dynamics. When evaluated across seven diverse datasets: ETTh1, ETTh2, ETTm1, ETTm2 (electricity transformer temperature), and Waste, Solar, and Hydro (renewable energy), this architecture consistently outperforms state-of-the-art baselines in various forecasting metrics, proving its robustness in capturing complex temporal dependencies. Furthermore, the model enhances interpretability through SHAP analysis, making it suitable for sustainable energy applications.

This paper introduces Recurrent Expansion (RE) as a new learning paradigm that advances beyond conventional Machine Learning (ML) and Deep Learning (DL). While DL focuses on learning from static data representations, RE proposes an additional dimension: learning from the evolving behavior of models themselves. RE emphasizes multiple mappings of data through identical deep architectures and analyzes their internal representations (i.e., feature maps) in conjunction with observed performance signals such as loss. By incorporating these behavioral traces, RE enables iterative self-improvement, allowing each model version to gain insight from its predecessors. The framework is extended through Multiverse RE (MVRE), which aggregates signals from parallel model instances, and further through Heterogeneous MVRE (HMVRE), where models of varying architectures contribute diverse perspectives. A scalable and adaptive variant, Sc-HMVRE, introduces selective mechanisms and scale diversity for real-world deployment. Altogether, RE presents a shift in DL: from purely representational learning to behavior-aware, self-evolving systems. It lays the groundwork for a new class of intelligent models capable of reasoning over their own learning dynamics, offering a path toward scalable, introspective, and adaptive artificial intelligence. A simple code example to support beginners in running their own experiments is provided in Code Availability Section of this paper.