With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex multi-scenario, multi-objective problem. Although expert engineers have developed numerous domain specific models (DSMs) to address distinct technical problems, mastering, integrating, and orchestrating these heterogeneous DSMs still entail considerable overhead for ADN operators. Therefore, an intelligent approach is urgently required to unify these DSMs and enable efficient coordination. To address this challenge, this paper proposes the ADN-Agent architecture, which leverages a general large language model (LLM) to coordinate multiple DSMs, enabling adaptive intent recognition, task decomposition, and DSM invocation. Within the ADN-Agent, we design a novel communication mechanism that provides a unified and flexible interface for diverse heterogeneous DSMs. Finally, for some language-intensive subtasks, we propose an automated training pipeline for fine-tuning small language models, thereby effectively enhancing the overall problem-solving capability of the system. Comprehensive comparisons and ablation experiments validate the efficacy of the proposed method and demonstrate that the ADN-Agent architecture outperforms existing LLM application paradigms.

Abstract-- Hybrid dynamical systems result from the interaction of continuous-variable dynamics with discrete events and encompass various systems such as legged robots, vehicles and aircrafts. Challenges arise when the system's modes are characterized by unobservable (latent) parameters and the events that cause system dynamics to switch between different modes are also unobservable. Model-based control approaches typically do not account for such uncertainty in the hybrid dynamics, while standard model-free RL methods fail to account for abrupt mode switches, leading to poor generalization. T o overcome this, we propose SAC-MoE which models the actor of the Soft Actor-Critic (SAC) framework as a Mixture of Experts (MoE) with a learned router that adaptively selects among learned experts. T o further improve robustness, we develop a curriculum-based training algorithm to prioritize data collection in challenging settings, allowing better generalization to unseen modes and switching locations. Simulation studies in hybrid autonomous racing and legged locomotion tasks show that SAC-MoE outperforms baselines (up to 6x) in zero-shot generalization to unseen environments. Our curriculum strategy consistently improves performance across all evaluated policies. Qualitative analysis shows that the interpretable MoE router activates different experts for distinct latent modes. Reinforcement Learning (RL) algorithms are typically developed under the assumption of continuous, stationary system dynamics that are invariant to the environment that a system is operating in.

Large Language Models (LLMs) are becoming increasingly data-intensive due to growing model sizes, and they are becoming memory-bound as the context length and, consequently, the key-value (KV) cache size increase. Inference, particularly the decoding phase, is dominated by memory-bound GEMV or flat GEMM operations with low operational intensity (OI), making it well-suited for processing-in-memory (PIM) approaches. However, existing in/near-memory solutions face critical limitations such as reduced memory capacity due to the high area cost of integrating processing elements (PEs) within DRAM chips, and limited PE capability due to the constraints of DRAM fabrication technology. This work presents a chiplet-based memory module that addresses these limitations by decoupling logic and memory into chiplets fabricated in heterogeneous technology nodes and connected via an interposer. The logic chiplets sustain high bandwidth access to the DRAM chiplets, which house the memory banks, and enable the integration of advanced processing components such as systolic arrays and SRAM-based buffers to accelerate memory-bound GEMM kernels, capabilities that were not feasible in prior PIM architectures. We propose Sangam, a CXL-attached PIM-chiplet based memory module that can either act as a drop-in replacement for GPUs or co-executes along side the GPUs. Sangam achieves speedup of 3.93, 4.22, 2.82x speedup in end-to-end query latency, 10.3, 9.5, 6.36x greater decoding throughput, and order of magnitude energy savings compared to an H100 GPU for varying input size, output length, and batch size on LLaMA 2-7B, Mistral-7B, and LLaMA 3-70B, respectively.

We approach the search for optimal element ordering in bimetallic alloy nanoparticles (NPs) as a reinforcement learning (RL) problem, and have built an RL agent that learns to perform such global optimisation using the geometric graph representation of the NPs. To demonstrate the effectiveness, we train an RL agent to perform composition-conserving atomic swap actions on the icosahedral nanoparticle structure. Trained once on randomised $Ag_{X}Au_{309-X}$ compositions and orderings, the agent discovers previously established ground state structure. We show that this optimization is robust to differently ordered initialisations of the same NP compositions. We also demonstrate that a trained policy can extrapolate effectively to NPs of unseen size. However, the efficacy is limited when multiple alloying elements are involved. Our results demonstrate that RL with pre-trained equivariant graph encodings can navigate combinatorial ordering spaces at the nanoparticle scale, and offer a transferable optimisation strategy with the potential to generalise across composition and reduce repeated individual search cost.

This study presents an AI enhanced IoT framework for predictive maintenance and affordability optimization in smart microgrids using a Digital Twin modeling approach. The proposed system integrates real time sensor data, machine learning based fault prediction, and cost aware operational analytics to improve reliability and energy efficiency in distributed microgrid environments. By synchronizing physical microgrid components with a virtual Digital Twin, the framework enables early detection of component degradation, dynamic load management, and optimized maintenance scheduling. Experimental evaluations demonstrate improved predictive accuracy, reduced operational downtime, and measurable cost savings compared to baseline microgrid management methods. The findings highlight the potential of Digital Twin driven IoT architectures as a scalable solution for next generation intelligent and affordable energy systems.

Non-intrusive load monitoring (NILM) is an advanced load monitoring technique that uses data-driven algorithms to disaggregate the total power consumption of a household into the consumption of individual appliances. However, real-world NILM deployment still faces major challenges, including overfitting, low model generalization, and disaggregating a large number of appliances operating at the same time. To address these challenges, this work proposes an end-to-end framework for the NILM classification task, which consists of high-frequency labeled data, a feature extraction method, and a lightweight neural network. Within this framework, we introduce a novel feature extraction method that fuses Independent Component Analysis (ICA) and Principal Component Analysis (PCA) features. Moreover, we propose a lightweight architecture for multi-label NILM classification (Fusion-ResNet). The proposed feature-based model achieves a higher $F1$ score on average and across different appliances compared to state-of-the-art NILM classifiers while minimizing the training and inference time. Finally, we assessed the performance of our model against baselines with a varying number of simultaneously active devices. Results demonstrate that Fusion-ResNet is relatively robust to stress conditions with up to 15 concurrently active appliances.

We present TEMPO, a global, temporally resolved dataset of building density and height derived from high-resolution satellite imagery using deep learning models. We pair building footprint and height data from existing datasets with quarterly PlanetScope basemap satellite images to train a multi-task deep learning model that predicts building density and building height at a 37.6-meter per pixel resolution. We apply this model to global PlanetScope basemaps from Q1 2018 through Q2 2025 to create global, temporal maps of building density and height. We validate these maps by comparing against existing building footprint datasets. Our estimates achieve an F1 score between 85% and 88% on different hand-labeled subsets, and are temporally stable, with a 0.96 five-year trend-consistency score. TEMPO captures quarterly changes in built settlements at a fraction of the computational cost of comparable approaches, unlocking large-scale monitoring of development patterns and climate impacts essential for global resilience and adaptation efforts.

We apply preference learning to the task of language model-guided design of novel structural alloys. In contrast to prior work that focuses on generating stable inorganic crystals, our approach targets the synthesizeability of a specific structural class: BCC/B2 superalloys, an underexplored family of materials with potential applications in extreme environments. Using three open-weight models (LLaMA-3.1, Gemma-2, and OLMo-2), we demonstrate that language models can be optimized for multiple design objectives using a single, unified reward signal through Direct Preference Optimization (DPO). Unlike prior approaches that rely on heuristic or human-in-the-loop feedback (costly), our reward signal is derived from thermodynamic phase calculations, offering a scientifically grounded criterion for model tuning. To our knowledge, this is the first demonstration of preference-tuning a language model using physics-grounded feedback for structural alloy design. The resulting framework is general and extensible, providing a path forward for intelligent design-space exploration across a range of physical science domains.

Abstract-- Robotic exploration in extreme environments--such as caves, oceans, and planetary surfaces--poses significant challenges, particularly in locomotion across diverse terrains. Conventional wheeled or legged robots often struggle in these contexts due to surface variability. This paper presents ARCSnake V2, an amphibious, screw-propelled, snake-like robot designed for teleoperated or autonomous locomotion across land, granular media, and aquatic environments. ARCSnake V2 combines the high mobility of hyper-redundant snake robots with the terrain versatility of Archimedean screw propulsion. Key contributions include a water-sealed mechanical design with serially linked screw and joint actuation, an integrated buoyancy control system, and teleoperation via a kinematically-matched handheld controller . The robot's design and control architecture enable multiple locomotion modes--screwing, wheeling, and sidewinding--with smooth transitions between them. Robotic exploration in extreme environments, such as caves, oceans and planetary surfaces, poses significant challenges for the diverse set of terrains [1].

Abstract--Federated Learning (FL) is a powerful paradigm for distributed learning, but its increasing complexity leads to significant energy consumption from client-side computations for training models. In particular, the challenge is critical in energy-harvesting FL (EHFL) systems where participation availability of each device oscillates due to limited energy. T o address this, we propose FedBacys, a battery-aware EHFL framework using cyclic client participation based on users' battery levels. By clustering clients and scheduling them sequentially, Fed-Bacys minimizes redundant computations, reduces system-wide energy usage, and improves learning stability. We also introduce FedBacys-Odd, a more energy-efficient variant that allows clients to participate selectively, further reducing energy costs without compromising performance. We provide a convergence analysis for our framework and demonstrate its superior energy efficiency and robustness compared to existing algorithms through numerical experiments. Federated learning (FL) [2] is a distributed optimization framework that has seen rapid growth due to its ability to enable privacy-preserving collaborative learning. As intelligent services are increasingly deployed on battery-powered edge devices, ensuring sustainable FL has become critical [3].