Link prediction infers missing or future relations between graph nodes, based on connection patterns. Scientific literature networks and knowledge graphs are typically large, sparse, and noisy, and often contain missing links between entities. We present an AI-driven hierarchical link prediction framework that integrates matrix factorization to infer hidden associations and steer discovery in complex material domains. Our method combines Hierarchical Nonnegative Matrix Factorization (HNMFk) and Boolean matrix factorization (BNMFk) with automatic model selection, as well as Logistic matrix factorization (LMF), we use to construct a three-level topic tree from a 46,862-document corpus focused on 73 transition-metal dichalcogenides (TMDs). These materials are studied in a variety of physics fields with many current and potential applications. An ensemble BNMFk + LMF approach fuses discrete interpretability with probabilistic scoring. The resulting HNMFk clusters map each material onto coherent topics like superconductivity, energy storage, and tribology. Also, missing or weakly connected links are highlight between topics and materials, suggesting novel hypotheses for cross-disciplinary exploration. We validate our method by removing publications about superconductivity in well-known superconductors, and show the model predicts associations with the superconducting TMD clusters. This shows the method finds hidden connections in a graph of material to latent topic associations built from scientific literature, especially useful when examining a diverse corpus of scientific documents covering the same class of phenomena or materials but originating from distinct communities and perspectives. The inferred links generating new hypotheses, produced by our method, are exposed through an interactive Streamlit dashboard, designed for human-in-the-loop scientific discovery.

Scrubbing surfaces is a physically demanding and time-intensive task. Removing adhered contamination requires substantial friction generated through pressure and torque or high lateral forces. Rigid robotic manipulators, while capable of exerting these forces, are usually confined to structured environments isolated from humans due to safety risks. In contrast, soft robot arms can safely work around humans and adapt to environmental uncertainty, but typically struggle to transmit the continuous torques or lateral forces necessary for scrubbing. Here, we demonstrate a soft robotic arm scrubbing adhered residues using torque and pressure, a task traditionally challenging for soft robots. We train a neural network to learn the arm's inverse kinematics and elasticity, which enables open-loop force and position control. Using this learned model, the robot successfully scrubbed burnt food residue from a plate and sticky fruit preserve from a toilet seat, removing an average of 99.7% of contamination. This work demonstrates how soft robots, capable of exerting continuous torque, can effectively and safely scrub challenging contamination from surfaces.

Machine learning (ML) is widely used to model chaotic systems. Among ML approaches, echo state networks (ESNs) have received considerable attention due to their simple construction and fast training. However, ESN performance is highly sensitive to hyperparameter choices and to its random initialization. In this work, we demonstrate that ESNs constructed using deterministic rules and simple topologies (MESNs) outperform standard ESNs in the task of chaotic attractor reconstruction. We use a dataset of more than 90 chaotic systems to benchmark 10 different minimal deterministic reservoir initializations. We find that MESNs obtain up to a 41% reduction in error compared to standard ESNs. Furthermore, we show that the MESNs are more robust, exhibiting less inter-run variation, and have the ability to reuse hyperparameters across different systems. Our results illustrate how structured simplicity in ESN design can outperform stochastic complexity in learning chaotic dynamics.

This paper has been accepted for publication at the International Workshop on Advances in Sensors and Interfaces (IW ASI), Italy, 2025. DOI: T o be added when available. Abstract -- Data Compression is a staple of data processing and storage. Sending and storing data more efficiently is an open challenge in the Internet-of-Things (IoT), with devices typically characterized by limited availability of energy and computing power . The problem tackled in this paper is the massive amounts of sensor data collected and sent uncompressed by IoT-devices. We address this issue by compressing local data using a neural network supplemented with the Residual V ector Quantization (RVQ) technique. This paper, inspired by lossy neural compressors for audio like Google Soundstream and Meta EnCodec, proposes EdgeCodec: a lightweight lossy neural compressor specifically designed to run at the edge on low-power and resource constrained Microcontroller Units (MCUs). EdgeCodec processes multi-channel data with a flexible end-to-end learnable pipeline. We evaluate EdgeCodec in a real-life challenging use case, namely wind turbine monitoring using a 40-channel barometric sensor . Under the proposed use-case, our EdgeCodec reaches a Compression Ratio (CR) between 2560 and 10240 that can be varied in real-time to tune the tradeoff between compression and reconstruction quality.

A common training approach for language models involves using a large-scale language model to expand a human-provided dataset, which is subsequently used for model training.This method significantly reduces training costs by eliminating the need for extensive human data annotation. However, it still faces challenges such as high carbon emissions during data augmentation and the risk of data leakage when we use closed-source LLMs. To address these issues, we propose a self-evolution method for language models. First, we introduce the Multi-level Principle Generation, which enables a large-scale model to summarize task-completion principles based on a small amount of task data. Then, we propose the Principle-based Instance Generation, in which a smaller-scale language model uses these task principles to generate a large amount of data. This data is then used for model training. Experimental results show that our proposed method significantly improves model performance compared to directly using a smaller-scale language model to generate data. Additionally, since we only use the large-scale language model to generate the task-completion principles, the carbon emissions associated with training the model are greatly reduced.

Underwater Acoustic Networks (UANs) have gained significant attention from both industry and academia due to their indisputable advantages in improving link reliability, increasing system capacity, expanding transmission range and so on. Acoustic communication is most widely used underwater communication as sound wave is not absorbed by water so easily like electromagnetic wave and optical wave [1]. UANs typically consist of acoustic-linked seabed sensors, autonomous underwater vehicles, and ground stations that provide links to onshore control centers. Due to the battery-powered network nodes, shallow water acoustic channel characteristics, such as low available bandwidth and highly varying multi-path, maximizing throughput while minimizing consumption has become a very challenging task [2]. Recent studies have discussed the challenges and opportunities of underwater cognitive communication [3], proposed cooperative automatic repeat request protocols for higher channel quality [4], and analyzed the impact of low transmission rates and long preambles on medium access control protocols [5]. Artificial intelligence (AI) has experienced significant growth in popularity in recent years, and many industries and research fields have explored its potential applications, including information theory, game theory, biological systems, and so on [6-9].

--Modern power systems face significant challenges in state estimation and real-time monitoring, particularly regarding response speed and accuracy under faulty conditions or cyber-attacks. This paper proposes a hybrid approach using physics-informed neural networks (PINNs) to enhance the accuracy and robustness, of power system state estimation. By embedding physical laws into the neural network architecture, PINNs improve estimation accuracy for transmission grid applications under both normal and faulty conditions, while also showing potential in addressing security concerns such as data manipulation attacks. Experimental results show that the proposed approach outperforms traditional machine learning models, achieving up to 83% higher accuracy on unseen subsets of the training dataset and 65% better performance on entirely new, unrelated datasets. Experiments also show that during a data manipulation attack against a critical bus in a system, the PINN can be up to 93% more accurate than an equivalent neural network. The escalating global electricity demand, driven by rapid urbanization, transportation electrification, and digital technology proliferation, has underscored the need for robust and stable power systems. Ensuring the stability and security of critical infrastructures, particularly power transmission networks, is essential for economic stability and public safety. However, the growing complexity of modern grids, driven by renewable energy integration, adoption of smart grid technologies, and interconnected networks, presents significant challenges in monitoring, control, and system resilience [1], [2]. In particular, addressing challenges related to real-time data management and stability has become increasingly critical, necessitating advanced monitoring schemes to ensure system stability and integrity.

Politecnico di Torino, ItalyAbstract: Roll stabilization is a critical aspect of ship motion control, particularly for vessels operating in low-speed or zero-speed conditions, where traditional hydrodynamic fins lose their effectiveness. In this paper, we consider a roll damping system, developed by Navis JSC, based on two actively controlled zero-speed fins. Unlike conventional fin stabilizers, zero-speed fins employ a drag-based mechanism and active oscillations to generate stabilizing forces even when the vessel is stationary. We propose a simple linear control architecture that, however, accounts for nonlinear drag forces and actuator limitations. Simulation results on a high-fidelity vessel model used for HIL testing demonstrate the effectiveness of the proposed approach.

AI-based methods have revolutionized atmospheric forecasting, with recent successes in medium-range forecasting spurring the development of climate foundation models. Accurate modeling of complex atmospheric dynamics at high spatial resolutions and longer lead times requires large neural networks and gigabyte-sized data samples, making accelerator memory and I/O-bandwidth the bottlenecks for model training. We introduce WeatherMixer, a multi-layer-perceptron-based architecture whose workload scales linearly with input size, allowing the model to learn global weather phenomena at accuracies similar to numerical weather prediction. To cope with the computational demand, we propose Jigsaw, a novel model parallelization scheme that employs both domain and tensor parallelism, eliminating memory redundancy. Jigsaw exceeds state-of-the-art performance in strong scaling in compute-communication-limited systems and achieves superscalar weak scaling in I/O-bandwidth-limited systems. We scale training to 256 GPUs, reaching peak performances of 9 and 11 PFLOPs, 23% and 28% of theoretical peaks, achieving 68% and 72% scaling efficiency versus 51% without model parallelism.

Covering 89 elements, MP-ALOE was created using active learning and primarily consists of off-equilibrium structures. We benchmark a machine learning interatomic potential trained on MP-ALOE, and evaluate its performance on a series of benchmarks, including predicting the thermochemical properties of equilibrium structures; predicting forces of far-from-equilibrium structures; maintaining physical soundness under static extreme deformations; and molecular dynamic stability under extreme temperatures and pressures. MP-ALOE shows strong performance on all of these benchmarks, and is made public for the broader community to utilize.