--While foundation AI models excel at tasks like classification and decision-making, their high energy consumption makes them unsuitable for energy-constrained applications. Inspired by the brain's efficiency, spiking neural networks (SNNs) have emerged as a viable alternative due to their event-driven nature and compatibility with neuromorphic chips. This work introduces a novel system that combines knowledge distillation and ensemble learning to bridge the performance gap between artificial neural networks (ANNs) and SNNs. A foundation AI model acts as a teacher network, guiding smaller student SNNs organized into an ensemble, called Spiking Neural Ensemble (SNE). SNE enables the disentanglement of the teacher's knowledge, allowing each student to specialize in predicting a distinct aspect of it, while processing the same input. The core innovation of SNE is the adaptive activation of a subset of SNN models of an ensemble, leveraging knowledge-distillation, enhanced with an informed-partitioning (disentanglement) of the teacher's feature space. Moreover, SNE is significantly more efficient than the teacher network, reducing computational requirements by up to 20x with only a 2% drop in accuracy on the CIF AR-10 dataset. This disentanglement procedure achieves an accuracy improvement of up to 2.4% on the CIF AR-10 dataset compared to other partitioning schemes. Finally, we comparatively analyze SNE performance under noisy conditions, demonstrating enhanced robustness compared to its ANN teacher . In summary, SNE offers a promising new direction for energy-constrained applications. Foundation AI is repeatedly breaking ground in computer vision and machine learning [1], [2], with advancements at dramatic speed across various domains, including image and video classification, semantic segmentation, depth estimation, image captioning, and decision-making.

Figure 1: Many everyday mobile manipulation tasks require reaching a precise interaction site before executing a motion primitive, e.g. Open loop execution is unable to meet the high-precision needed for these tasks. In this paper, we develop Servoing with Vision Models (SVM), a training-free framework that closes the loop to enable a commodity mobile manipulator to tackle these tasks. Abstract -- Many everyday mobile manipulation tasks require precise interaction with small objects, such as grasping a knob to open a cabinet or pressing a light switch. In this paper, we develop Servoing with Vision Models (SVM), a closed-loop training-free framework that enables a mobile manipulator to tackle such precise tasks involving the manipulation of small objects. SVM employs an RGB-D wrist camera and uses visual servoing for control. Our novelty lies in the use of state-of-the-art vision models to reliably compute 3D targets from the wrist image for diverse tasks and under occlusion due to the end-effector . T o mitigate occlusion artifacts, we employ vision models to out-paint the end-effector thereby significantly enhancing target localization. We demonstrate that aided by out-painting methods, open-vocabulary object detectors can serve as a drop-in module to identify semantic targets ( e.g.

The use of transition group metals in electric batteries requires extensive usage of critical elements like lithium, cobalt and nickel, which poses significant environmental challenges. Replacing these metals with redox-active organic materials offers a promising alternative, thereby reducing the carbon footprint of batteries by one order of magnitude. However, this approach faces critical obstacles, including the limited availability of suitable redox-active organic materials and issues such as lower electronic conductivity, voltage, specific capacity, and long-term stability. To overcome the limitations for lower voltage and specific capacity, a machine learning (ML) driven battery informatics framework is developed and implemented. This framework utilizes an extensive battery dataset and advanced ML techniques to accelerate and enhance the identification, optimization, and design of redox-active organic materials. In this contribution, a data-fusion ML coupled meta learning model capable of predicting the battery properties, voltage and specific capacity, for various organic negative electrodes and charge carriers (positive electrode materials) combinations is presented. The ML models accelerate experimentation, facilitate the inverse design of battery materials, and identify suitable candidates from three extensive material libraries to advance sustainable energy-storage technologies.

Estimating the construction year of buildings is of great importance for sustainability. Sustainable buildings minimize energy consumption and are a key part of responsible and sustainable urban planning and development to effectively combat climate change. By using Artificial Intelligence (AI) and recently proposed Transformer models, we are able to estimate the construction epoch of buildings from a multi-modal dataset. In this paper, we introduce a new benchmark multi-modal dataset, i.e. the Map your City Dataset (MyCD), containing top-view Very High Resolution (VHR) images, Earth Observation (EO) multi-spectral data from the Copernicus Sentinel-2 satellite constellation, and street-view images in many different cities in Europe, co-localized with respect to the building under study and labelled with the construction epoch. We assess EO generalization performance on new/ previously unseen cities that have been held-out from training and appear only during inference. In this work, we present the community-based data challenge we organized based on MyCD. The ESA AI4EO Challenge MapYourCity was opened in 2024 for 4 months. Here, we present the Top-4 performing models, and the main evaluation results. During inference, the performance of the models using both all three input modalities and only the two top-view modalities, i.e. without the street-view images, is examined. The evaluation results show that the models are effective and can achieve good performance on this difficult real-world task of estimating the age of buildings, even on previously unseen cities, as well as even using only the two top-view modalities (i.e. VHR and Sentinel-2) during inference.

--Performing accurate confidence quantification and assessment in pixel-wise regression tasks, which are downstream applications of AI Foundation Models for Earth Observation (EO), is important for deep neural networks to predict their failures, improve their performance and enhance their capabilities in real-world applications, for their practical deployment. For pixel-wise regression tasks, specifically utilizing remote sensing data from satellite imagery in EO Foundation Models, confidence quantification is a critical challenge. The focus of this research is on developing a Foundation Model using EO satellite data that computes and assigns a confidence metric alongside regression outputs to improve the reliability and interpretability of predictions generated by deep neural networks. T o this end, we develop, train and evaluate the proposed Confidence-A ware Regression Estimation (CARE) Foundation Model. Our model CARE computes and assigns confidence to regression results as downstream tasks of a Foundation Model for EO data, and performs a confidence-aware self-corrective learning method for the low-confidence regions. We evaluate the model CARE, and experimental results on multi-spectral data from the Copernicus Sentinel-2 constellation to estimate the building density (i.e. We also show that our model CARE outperforms other methods. The significance of confidence quantification and assessment in deep learning, specifically in AI Foundation Models in Earth Observation (EO) that use satellite data, for regression applications is critical. The utility of satellite data seems inexhaustible, and thanks to developments in AI, applications emerge at an accelerated pace in EO Foundation Models using remote sensing data.

Multi-Party Conversations (MPCs) are widely studied across disciplines, with social media as a primary data source due to their accessibility. However, these datasets raise privacy concerns and often reflect platform-specific properties. For example, interactions between speakers may be limited due to rigid platform structures (e.g., threads, tree-like discussions), which yield overly simplistic interaction patterns (e.g., as a consequence of ``reply-to'' links). This work explores the feasibility of generating diverse MPCs with instruction-tuned Large Language Models (LLMs) by providing deterministic constraints such as dialogue structure and participants' stance. We investigate two complementary strategies of leveraging LLMs in this context: (i.) LLMs as MPC generators, where we task the LLM to generate a whole MPC at once and (ii.) LLMs as MPC parties, where the LLM generates one turn of the conversation at a time, provided the conversation history. We next introduce an analytical framework to evaluate compliance with the constraints, content quality, and interaction complexity for both strategies. Finally, we assess the quality of obtained MPCs via human annotation and LLM-as-a-judge evaluations. We find stark differences among LLMs, with only some being able to generate high-quality MPCs. We also find that turn-by-turn generation yields better conformance to constraints and higher linguistic variability than generating MPCs in one pass. Nonetheless, our structural and qualitative evaluation indicates that both generation strategies can yield high-quality MPCs.

The government approved separate plans Tuesday to reduce greenhouse gas emissions by 60% in the fiscal year from April 2035 -- and by 73% in fiscal 2040 -- compared with 2013 levels, and have renewables and nuclear power generate half and 20% of the country's electricity, respectively, by 2040. However, the new emissions target -- which follows one under the current energy plan for a 46% reduction by fiscal 2030 -- has been criticized as being insufficient to reach globally agreed climate targets. Concerns have also been raised over the decision-making process' speed and transparency. Japan has been cautious about increasing dependence on nuclear power following the triple meltdown at the Fukushima No. 1 nuclear power plant in 2011. But the government has made the shift amid predictions of higher electricity demand stemming from semiconductor production and data centers for artificial intelligence in the decades to come.

Ukraine's military said Russia launched a barrage of 147 attack drones against Ukraine overnight. Out of this, the Ukrainian Air Force reported shooting down 83, while 59 did not reach their targets. Several storage facilities and private residences were reported damaged. The Caspian Pipeline Consortium said that Ukrainian drones hit one of its major oil pipelines in southern Russia's Kropotkinskaya pumping station in the Krasnodar region, affecting supply from neighbouring Kazakhstan. Ukraine's Security Service claimed responsibility for the attack on the oil pipeline and said that Moscow's Ilsky oil refinery in Krasnodar was also hit, with at least 20 explosions heard in the area.

The combination of Spiking Neural Networks (SNNs) and Vision Transformers (ViTs) holds potential for achieving both energy efficiency and high performance, particularly suitable for edge vision applications. However, a significant performance gap still exists between SNN-based ViTs and their ANN counterparts. Here, we first analyze why SNN-based ViTs suffer from limited performance and identify a mismatch between the vanilla self-attention mechanism and spatio-temporal spike trains. This mismatch results in degraded spatial relevance and limited temporal interactions. To address these issues, we draw inspiration from biological saccadic attention mechanisms and introduce an innovative Saccadic Spike Self-Attention (SSSA) method. Specifically, in the spatial domain, SSSA employs a novel spike distribution-based method to effectively assess the relevance between Query and Key pairs in SNN-based ViTs. Temporally, SSSA employs a saccadic interaction module that dynamically focuses on selected visual areas at each timestep and significantly enhances whole scene understanding through temporal interactions. Building on the SSSA mechanism, we develop a SNN-based Vision Transformer (SNN-ViT). Extensive experiments across various visual tasks demonstrate that SNN-ViT achieves state-of-the-art performance with linear computational complexity. The effectiveness and efficiency of the SNN-ViT highlight its potential for power-critical edge vision applications.

In this work, an experimental characterization of the configuration space of a soft, pneumatically actuated morphing quadrotor is presented, with a focus on precise thrust characterization of its flexible arms, considering the effect of downwash. Unlike traditional quadrotors, the soft drone has pneumatically actuated arms, introducing complex, nonlinear interactions between motor thrust and arm deformation, which make precise control challenging. The silicone arms are actuated using differential pressure to achieve flexibility and thus have a variable workspace compared to their fixed counter-parts. The deflection of the soft arms during compression and expansion is controlled throughout the flight. However, in real time, the downwash from the motor attached at the tip of the soft arm generates a significant and random disturbance on the arm. This disturbance affects both the desired deflection of the arm and the overall stability of the system. To address this factor, an experimental characterization of the effect of downwash on the deflection angle of the arm is conducted.