The deployment of machine learning (ML) models on microcontrollers (MCUs) is constrained by strict energy, latency, and memory requirements, particularly in battery - operated and real - time edge devices. While software - level optimizations such as quantizatio n and pruning reduce model size and computation, hardware acceleration has emerged as a decisive enabler for efficient embedded inference. This paper evaluates the impact of Neural Processing Units (NPUs) on MCU - based ML execution, using the ARM Cortex - M55 core combined with the Ethos - U55 NPU on the Alif Semiconductor Ensemble E7 development board as a representative platform. A rigorous measurement methodology was employed, incorporating per - inference net energy accounting via GPIO - triggered high - resolutio n digital multimeter synchronization and idle - state subtraction, ensuring accurate attribution of energy costs. Experimental results across six representative ML models -- including MiniResNet, MobileNetV2, FD - MobileNet, MNIST, TinyYolo, and SSD - MobileNet -- dem onstrate substantial efficiency gains when inference is offloaded to the NPU. For moderate to large networks, latency improvements ranged from 7 to over 125, with per - inference net energy reductions up to 143 . Notably, the NPU enabled execution of model s unsupported on CPU - only paths, such as SSD - MobileNet, highlighting its functional as well as efficiency advantages. These findings establish NPUs as a cornerstone of energy - aware embedded AI, enabling real - time, power - constrained ML inference at the MCU level.

Temporal Change Description (TCD) and Future Satellite Image Forecasting (FSIF) are critical, yet historically disjointed tasks in Satellite Image Time Series (SITS) analysis. Both are fundamentally limited by the common challenge of modeling long-range temporal dynamics. To explore how to improve the performance of methods on both tasks simultaneously by enhancing long-range temporal understanding capabilities, we introduce TAMMs, the first unified framework designed to jointly perform TCD and FSIF within a single MLLM-diffusion architecture. TAMMs introduces two key innovations: Temporal Adaptation Modules (TAM) enhance frozen MLLM's ability to comprehend long-range dynamics, and Semantic-Fused Control Injection (SFCI) mechanism translates this change understanding into fine-grained generative control. This synergistic design makes the understanding from the TCD task to directly inform and improve the consistency of the FSIF task. Extensive experiments demonstrate TAMMs significantly outperforms state-of-the-art specialist baselines on both tasks.

While it is expected to build robotic limbs with multiple degrees of freedom (DoF) inspired by nature, a single DoF design remains fundamental, providing benefits that include, but are not limited to, simplicity, robustness, cost-effectiveness, and efficiency. Mechanisms, especially those with multiple links and revolute joints connected in closed loops, play an enabling factor in introducing motion diversity for 1-DoF systems, which are usually constrained by self-collision during a full-cycle range of motion. This study presents a novel computational approach to designing one-degree-of-freedom (1-DoF) overconstrained robotic limbs for a desired spatial trajectory, while achieving energy-efficient, self-collision-free motion in full-cycle rotations. Firstly, we present the geometric optimization problem of linkage-based robotic limbs in a generalized formulation for self-collision-free design. Next, we formulate the spatial trajectory generation problem with the overconstrained linkages by optimizing the similarity and dynamic-related metrics. We further optimize the geometric shape of the overconstrained linkage to ensure smooth and collision-free motion driven by a single actuator. We validated our proposed method through various experiments, including personalized automata and bio-inspired hexapod robots. The resulting hexapod robot, featuring overconstrained robotic limbs, demonstrated outstanding energy efficiency during forward walking.

The analysis of complex building time-series for actionable insights and recommendations remains challenging due to the nonlinear and multi-scale characteristics of energy data. To address this, we propose a framework that fine-tunes visual language large models (VLLMs) on 3D graphical representations of the data. The approach converts 1D time-series into 3D representations using continuous wavelet transforms (CWTs) and recurrence plots (RPs), which capture temporal dynamics and localize frequency anomalies. These 3D encodings enable VLLMs to visually interpret energy-consumption patterns, detect anomalies, and provide recommendations for energy efficiency. We demonstrate the framework on real-world building-energy datasets, where fine-tuned VLLMs successfully monitor building states, identify recurring anomalies, and generate optimization recommendations. Quantitatively, the Idefics-7B VLLM achieves validation losses of 0.0952 with CWTs and 0.1064 with RPs on the University of Sharjah energy dataset, outperforming direct fine-tuning on raw time-series data (0.1176) for anomaly detection. This work bridges time-series analysis and visualization, providing a scalable and interpretable framework for energy analytics.

Robotic manipulators capable of regulating both compliance and stiffness offer enhanced operational safety and versatility. Here, we introduce Worm Gear-based Adaptive Variable Elasticity (WAVE), a variable stiffness actuator (VSA) that integrates a non-backdrivable worm gear. By decoupling the driving motor from external forces using this gear, WAVE enables precise force transmission to the joint, while absorbing positional discrepancies through compliance. WAVE is protected from excessive loads by converting impact forces into elastic energy stored in a spring. In addition, the actuator achieves continuous joint stiffness modulation by changing the spring's precompression length. We demonstrate these capabilities, experimentally validate the proposed stiffness model, show that motor loads approach zero at rest--even under external loading--and present applications using a manipulator with WAVE. This outcome showcases the successful decoupling of external forces. The protective attributes of this actuator allow for extended operation in contact-intensive tasks, and for robust robotic applications in challenging environments.

Predicting material properties is crucial for designing better batteries, semiconductors, and medical devices. Deep learning helps scientists quickly find promising materials by predicting their energy, forces, and stresses. Companies scale capacities of deep learning models in multiple domains, such as language modeling, and invest many millions of dollars into such models. Our team analyzes how scaling training data (giving models more information to learn from), model sizes (giving models more capacity to learn patterns), and compute (giving models more computational resources) for neural networks affects their performance for material property prediction. In particular, we trained both transformer and EquiformerV2 neural networks to predict material properties. We find empirical scaling laws for these models: we can predict how increasing each of the three hyperparameters (training data, model size, and compute) affects predictive performance. In particular, the loss $L$ can be measured with a power law relationship $L = α\cdot N^{-β}$, where $α$ and $β$ are constants while $N$ is the relevant hyperparameter. We also incorporate command-line arguments for changing training settings such as the amount of epochs, maximum learning rate, and whether mixed precision is enabled. Future work could entail further investigating scaling laws for other neural network models in this domain, such as GemNet and fully connected networks, to assess how they compare to the models we trained.

Accurately forecasting chaotic systems, prevalent in domains such as weather prediction and fluid dynamics, remains a significant scientific challenge. The inherent sensitivity of these systems to initial conditions, coupled with a scarcity of observational data, severely constrains traditional modeling approaches. Since these models are typically trained for a specific system, they lack the generalization capacity necessary for real-world applications, which demand robust zero-shot or few-shot forecasting on novel or data-limited scenarios. To overcome this generalization barrier, we propose ChaosNexus, a foundation model pre-trained on a diverse corpus of chaotic dynamics. ChaosNexus employs a novel multi-scale architecture named ScaleFormer augmented with Mixture-of-Experts layers, to capture both universal patterns and system-specific behaviors. The model demonstrates state-of-the-art zero-shot generalization across both synthetic and real-world benchmarks. On a large-scale testbed comprising over 9,000 synthetic chaotic systems, it improves the fidelity of long-term attractor statistics by more than 40% compared to the leading baseline. This robust performance extends to real-world applications with exceptional data efficiency. For instance, in 5-day global weather forecasting, ChaosNexus achieves a competitive zero-shot mean error below 1 degree, a result that further improves with few-shot fine-tuning. Moreover, experiments on the scaling behavior of ChaosNexus provide a guiding principle for scientific foundation models: cross-system generalization stems from the diversity of training systems, rather than sheer data volume.

Parameter-efficient fine-tuning (PEFT) methods must be resource-efficient yet handle heterogeneous reasoning transformations, and classical low-rank adaptation (LoRA) is constrained by the nominal rank $r$. Hadamard-style extensions like HiRA raise the nominal rank but couple every update to the global energy pattern of the frozen weight matrix, while ABBA trades this inductive bias for fully learned dense intermediates. To address the limitation of global modulation, we propose Block Hadamard high-Rank Adaptation (BHRA), which partitions each weight matrix and applies HiRA-style multiplicative modulation independently within every block, preserving the PEFT parameter footprint while unlocking localized rank amplification. Our empirical analyses reveal that this blockwise design maintains rich spectra across rank budgets, mitigating the collapse induced by global modulation. Across eight commonsense reasoning tasks and two arithmetic benchmarks with Llama-3.2 1B/3B, Mistral-7B, and Gemma-2 9B, BHRA consistently surpasses strong PEFT baselines under matched parameter budgets.

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the earlier stage of the training loop. These changes stabilize as training continues enabling them to be captured by matrices of a low intrinsic rank. Therefore, we propose an approach to identify such states of partial convergence and dynamically switch from full parameter training to Low Rank Adaptation (LoRA) on the ViT-Large model. W e introduce a flexible approach that leverages user-defined hyper-parameters to determine the switching point and assign a rank specific to each module layer based on its level of convergence. Experimental results show that this approach preserves model accuracy while reducing the number of train-able parameters to 10% of its original size, resulting in a 3 improvement in throughput, and a 1.5 reduction in average training time per epoch while also reducing GPU memory consumption by 20%.

This paper presents the design of a new soft-rigid robotic platform, "GeoGami". We leverage origami surface capabilities to achieve shape contraction and to support locomotion with underactuated forms. A key challenge is that origami surfaces have high degrees of freedom and typically require many actuators; we address repeatability by integrating surface compliance. We propose a mono-actuated GeoGami mobile platform that combines origami surface compliance with a geometric compliant skeleton, enabling the robot to transform and locomote using a single actuator. We demonstrate the robot, develop a stiffness model, and describe the central gearbox mechanism. We also analyze alternative cable-driven actuation methods for the skeleton to enable surface transformation. Finally, we evaluate the GeoGami platform for capabilities, including shape transformation and rolling. This platform opens new capabilities for robots that change shape to access different environments and that use shape transformation for locomotion.