Remote Sensing Image Captioning (RSIC) presents unique challenges and plays a critical role in applications. Traditional RSIC methods often struggle to produce rich and diverse descriptions. Recently, with advancements in VLMs, efforts have emerged to integrate these models into the remote sensing domain and to introduce descriptive datasets specifically designed to enhance VLM training. This paper proposes RS-MoE, a first Mixture of Expert based VLM specifically customized for remote sensing domain. Unlike traditional MoE models, the core of RS-MoE is the MoE Block, which incorporates a novel Instruction Router and multiple lightweight Large Language Models (LLMs) as expert models. The Instruction Router is designed to generate specific prompts tailored for each corresponding LLM, guiding them to focus on distinct aspects of the RSIC task. This design not only allows each expert LLM to concentrate on a specific subset of the task, thereby enhancing the specificity and accuracy of the generated captions, but also improves the scalability of the model by facilitating parallel processing of sub-tasks. Additionally, we present a two-stage training strategy for tuning our RS-MoE model to prevent performance degradation due to sparsity. We fine-tuned our model on the RSICap dataset using our proposed training strategy. Experimental results on the RSICap dataset, along with evaluations on other traditional datasets where no additional fine-tuning was applied, demonstrate that our model achieves state-of-the-art performance in generating precise and contextually relevant captions. Notably, our RS-MoE-1B variant achieves performance comparable to 13B VLMs, demonstrating the efficiency of our model design. Moreover, our model demonstrates promising generalization capabilities by consistently achieving state-of-the-art performance on the Remote Sensing Visual Question Answering (RSVQA) task.

We announce the release of EPT-1.5, the latest iteration in our Earth Physics Transformer (EPT) family of foundation AI earth system models. EPT-1.5 demonstrates substantial improvements over its predecessor, EPT-1. Built specifically for the European energy industry, EPT-1.5 shows remarkable performance in predicting energy-relevant variables, particularly 10m & 100m wind speed and solar radiation. Especially in wind prediction, it outperforms existing AI weather models like GraphCast, FuXi, and Pangu-Weather, as well as the leading numerical weather model, IFS HRES by the European Centre for Medium-Range Weather Forecasts (ECMWF), setting a new state of the art.

Current mainstream SAR image object detection methods still lack robustness when dealing with unknown objects in open environments. Open-set detection aims to enable detectors trained on a closed set to detect all known objects and identify unknown objects in open-set environments. The key challenges are how to improve the generalization to potential unknown objects and reduce the empirical classification risk of known categories under strong supervision. To address these challenges, a novel open-set aircraft detector for SAR images is proposed, named Open-Set Aircraft Detection (OSAD), which is equipped with three dedicated components: global context modeling (GCM), location quality-driven pseudo labeling generation (LPG), and prototype contrastive learning (PCL). GCM effectively enhances the network's representation of objects by attention maps which is formed through the capture of long sequential positional relationships. LPG leverages clues about object positions and shapes to optimize localization quality, avoiding overfitting to known category information and enhancing generalization to potential unknown objects. PCL employs prototype-based contrastive encoding loss to promote instance-level intra-class compactness and inter-class variance, aiming to minimize the overlap between known and unknown distributions and reduce the empirical classification risk of known categories. Extensive experiments have demonstrated that the proposed method can effectively detect unknown objects and exhibit competitive performance without compromising closed-set performance. The highest absolute gain which ranges from 0 to 18.36% can be achieved on the average precision of unknown objects.

Graph Neural Networks (GNN) are indispensable in learning from graph-structured data, yet their rising computational costs, especially on massively connected graphs, pose significant challenges in terms of execution performance. To tackle this, distributed-memory solutions such as partitioning the graph to concurrently train multiple replicas of GNNs are in practice. However, approaches requiring a partitioned graph usually suffer from communication overhead and load imbalance, even under optimal partitioning and communication strategies due to irregularities in the neighborhood minibatch sampling. This paper proposes practical trade-offs for improving the sampling and communication overheads for representation learning on distributed graphs (using popular GraphSAGE architecture) by developing a parameterized continuous prefetch and eviction scheme on top of the state-of-the-art Amazon DistDGL distributed GNN framework, demonstrating about 15-40% improvement in end-to-end training performance on the National Energy Research Scientific Computing Center's (NERSC) Perlmutter supercomputer for various OGB datasets.

Exploring the predictive capabilities of language models in material science is an ongoing interest. This study investigates the application of language model embeddings to enhance material property prediction in materials science. By evaluating various contextual embedding methods and pre-trained models, including Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT), we demonstrate that domain-specific models, particularly MatBERT significantly outperform general-purpose models in extracting implicit knowledge from compound names and material properties. Our findings reveal that information-dense embeddings from the third layer of MatBERT, combined with a context-averaging approach, offer the most effective method for capturing material-property relationships from the scientific literature. We also identify a crucial "tokenizer effect," highlighting the importance of specialized text processing techniques that preserve complete compound names while maintaining consistent token counts. These insights underscore the value of domain-specific training and tokenization in materials science applications and offer a promising pathway for accelerating the discovery and development of new materials through AI-driven approaches.

The search for weakly interacting matter particles (WIMPs) is one of the main objectives of the High Luminosity Large Hadron Collider (HL-LHC). In this work we use Machine-Learning (ML) techniques to explore WIMP radiative decays into a Dark Matter (DM) candidate in a supersymmetric framework. The minimal supersymmetric WIMP sector includes the lightest neutralino that can provide the observed DM relic density through its co-annihilation with the second lightest neutralino and lightest chargino. Moreover, the direct DM detection cross section rates fulfill current experimental bounds and provide discovery targets for the same region of model parameters in which the radiative decay of the second lightest neutralino into a photon and the lightest neutralino is enhanced. This strongly motivates the search for radiatively decaying neutralinos which, however, suffers from strong backgrounds. We investigate the LHC reach in the search for these radiatively decaying particles by means of cut-based and ML methods and estimate its discovery potential in this well-motivated, new physics scenario.

A piece of the radioactive fuel left from the meltdown of Japan's tsunami-hit Fukushima Daiichi nuclear power plant has been retrieved from the site using a remote-controlled robot. Investigators used the robot's fishing-rod-like arm to clip and collect a tiny piece of radioactive material from one of the plant's three damaged reactors – the first time such a feat has been achieved. Should it prove suitable for testing, scientists hope the sample will yield information that will help determine how to decommission the plant. The plant's manager, Tokyo Electric Power Company Holdings (Tepco), has said the sample was collected from the surface of a mound of molten debris that sits at the bottom of the Unit 2 reactor's primary containment vessel. The "telesco" robot, with its frontal tongs still holding the sample, returned to its enclosed container for safe storage after workers in full hazmat gear pulled it out of the containment vessel on Saturday.

This study presents a novel approach for quantificationally reconstructing density fields from shadowgraph images using physics-informed neural networks. The proposed method utilizes the shadowgraph technique visualizing the flow field, enabling reliable quantitative measurement of flow density fields. Compare to traditional methods, which obtain the distribution of physical quality in spatial coordinates case by case. We establish a new end-to-end network that directly from shadowgraph images to physical fields. Besides, the model employs a self-supervised learning approach, without any labeled data. Experimental validations across hot air jets, thermal plumes, and alcohol burner flames prove the model's accuracy and universality. This approach offers a non-invasive, real-time surrogate model for flow diagnostics. It is believed that this technique could cover and become a reliable tool in various scientific and engineering disciplines.

Expert systems are effective tools for automatically identifying energy efficiency potentials in manufacturing, thereby contributing significantly to global climate targets. These systems analyze energy data, pinpoint inefficiencies, and recommend optimizations to reduce energy consumption. Beyond systematic approaches for developing expert systems, there is a pressing need for simple and rapid software implementation solutions. Expert system shells, which facilitate the swift development and deployment of expert systems, are crucial tools in this process. They provide a template that simplifies the creation and integration of expert systems into existing manufacturing processes. This paper provides a comprehensive comparison of existing expert system shells regarding their suitability for improving energy efficiency, highlighting significant gaps and limitations. To address these deficiencies, we introduce a novel expert system shell, implemented in Jupyter Notebook, that provides a flexible and easily integrable solution for expert system development.

Autonomous vehicle (AV) motion planning problems often involve non-convex constraints, which present a major barrier to applying model predictive control (MPC) in real time on embedded hardware. This paper presents an approach for efficiently solving mixed-integer MPC motion planning problems using a hybrid zonotope representation of the obstacle-free space. The MPC optimization problem is formulated as a multi-stage mixed-integer quadratic program (MIQP) using a hybrid zonotope representation of the non-convex constraints. Risk-aware planning is supported by assigning costs to different regions of the obstacle-free space within the MPC cost function. A multi-stage MIQP solver is presented that exploits the structure of the hybrid zonotope constraints. For some hybrid zonotope representations, it is shown that the convex relaxation is tight, i.e., equal to the convex hull. In conjunction with logical constraints derived from the AV motion planning context, this property is leveraged to generate tight quadratic program (QP) sub-problems within a branch-and-bound mixed-integer solver. The hybrid zonotope structure is further leveraged to reduce the number of matrix factorizations that need to be computed within the QP sub-problems. Simulation studies are presented for obstacle-avoidance and risk-aware motion planning problems using polytopic maps and occupancy grids. In most cases, the proposed solver finds the optimal solution an order of magnitude faster than a state-of-the-art commercial solver. Processor-in-the-loop studies demonstrate the utility of the solver for real-time implementations on embedded hardware.