Large Language Models (LLMs) are increasingly applied to data-centric tasks in software maintenance and evolution, such as quality assurance and migration. While recent methods constrain LLM outputs using grammars or regular expressions, these syntactic techniques fail to enforce deeper semantic constraints involving numeric dependencies, conditional logic, and checksums. We present ClauseBandit, a framework that combines LLMs with Satisfiability Modulo Theories (SMT) solvers to generate structured data satisfying such constraints from natural language specifications. ClauseBandit introduces a Bayesian inference approach that selects the most plausible SMT formula using posterior probabilities derived from formula self-consistency and data likelihoods. Evaluated on 27 structured generation tasks inspired by industrial use-cases, ClauseBandit successfully selected valid SMT formulas for$\mathbf{7 4. 1 \%}$of tasks. Our approach enables LLM-based structured generation that goes beyond syntax, producing semantically valid, reusable constraint specifications from natural language.

This paper presents an investigation into the zero-shot performance of pre-trained foundation models on remote sensing tasks. Recent advances in self-supervised learning suggest that these models, when trained on vast amounts of unsupervised data, could potentially improve generalization across a number of downstream tasks. Our study offers an empirical evaluation of these models on standard remote-sensing benchmarks such as EuroSAT and BigEarthNet-S2, with the intent to confirm whether these models have encountered satellite imagery during their training phase. Moreover, we examine the impact of adding a geospatial domain-specific textual description of classes, contrasting it with the standard class-based prompts. Our findings indicate that the fine-tuned BLIP models exhibit superior zero-shot performance on these benchmarks compared to their standard counterparts, signifying that fine-tuning on standard benchmarks enhances performance. Furthermore, the addition of geospatial context variably influences performance depending on the specific model and dataset. This work provides crucial insights into the applicability of foundation models in remote sensing tasks and lays the groundwork for further research.

Large datasets of geospatial satellite images are available online, exhibiting significant variations in both image quality and content. These variations in image quality stem from the image processing pipeline and image acquisition settings, resulting in subtle differences within datasets of images acquired with the same satellites. Recent progress in the field of image processing have considerably enhanced capabilities in noise and artifacts removal, as well as image super-resolution. Consequently, this opens up possibilities for homogenizing geospatial image datasets by reducing the intra-dataset variations in image quality. In this work, we show that conventional image detection and segmentation neural networks trained on geospatial data are robust neither to noise and artefact removal preprocessing, nor to mild resolution variations.

Geospatial machine learning has seen tremendous aca-demic advancement, but its practical application has been constrained by difficulties with operationalizing performant and reliable solutions. Sourcing satellite imagery in real-world settings, handling terabytes of training data, and managing machine learning artifacts are a few of the chal-lenges that have severely limited downstream innovation. In this paper we introduce the GeoEngine11https://apps.granular.ai/apps platform for re-producible and production-ready geospatial machine learning research. GeoEngine removes key technical hurdles to adopting computer vision and deep learning-based geospa-tial solutions at scale. It is the first end-to-end geospatial machine learning platform, simplifying access to insights locked behind petabytes of imagery. Backed by a rigor-ous research methodology, this geospatial framework em-powers researchers with powerful abstractions for image sourcing, dataset development, model development, large scale training, and model deployment. In this paper we pro-vide the GeoEngine architecture explaining our design rationale in detail. We provide several real-world use cases of image sourcing, dataset development, and model building that have helped different organisations build and deploy geospatial solutions.

In this paper we introduce a novel platform for teams to develop rich, analysis-ready datasets for geospatial machine learning. Europa11https://europa.granular.ai addresses longstanding challenges that remote sensing and machine vision researchers face when developing datasets, including data sourcing, dataset development and sharing. By simplifying and accelerating the dataset creation process, Europa serves to expedite the pace of geospatial machine learning innovation. The platform enables users to develop feature-rich, spatio-temporal datasets using multiple sources of satellite imagery. Europa supports the development of datasets for segmentation, classification, object detection, and change detection problems. Europa also enables collaborative dataset development, with a management protocol for crowdsourcing labels and annotations. The web interface and API are built upon a resilient dataset management protocol that supports versioning, forking and access control, enabling greater research collaboration.

Heating, ventilation, and air-conditioning (HVAC) system’s supervisory control is crucial for energy-efficient thermal comfort in buildings. The control logic is usually specified as ‘if-then-that-else’ rules that capture the domain expertise of HVAC operators, but they often have conflicts that may lead to sub-optimal HVAC performance. We propose EImprove, a reinforcement-learning (RL) based framework that exploits these conflicts to learn a resolution policy. We evaluate EImprove through a co-simulation strategy involving EnergyPlus simulations of a real-world office setting and a formal requirement specifier. Our experiments show that EImprove learns 75% faster than a pure RL framework.

Sparsifying deep neural networks is of paramount interest in many areas, especially when those networks have to be implemented on low-memory devices. In this article, we propose a new formulation of the problem of generating sparse weights for a pre-trained neural network. By leveraging the properties of standard nonlinear activation functions, we show that the problem is equivalent to an approximate subdifferential inclusion problem. The accuracy of the approximation controls the sparsity. We show that the proposed approach is valid for a broad class of activation functions (ReLU, sigmoid, softmax). We propose an iterative optimization algorithm to induce sparsity whose convergence is guaranteed. Because of the algorithm flexibility, the sparsity can be ensured from partial training data in a minibatch manner. To demonstrate the effectiveness of our method, we perform experiments on various networks in different applicative contexts: image classification, speech recognition, natural language processing, and time-series forecasting.

Electrical motors are the most important source of mechanical energy in the industrial world. Their modeling traditionally relies on a physics-based approach, which aims at taking their complex internal dynamics into account. In this paper, we explore the feasibility of modeling the dynamics of an electrical motor by following a data-driven approach, which uses only its inputs and outputs and does not make any assumption on its internal behaviour. We propose a novel encoder-decoder architecture which benefits from recurrent skip connections. We also propose a novel loss function that takes into account the complexity of electrical motor quantities and helps in avoiding model bias. We show that the proposed architecture can achieve a good learning performance on our high-frequency high-variance datasets. Two datasets are considered: the first one is generated using a simulator based on the physics of an induction motor and the second one is recorded from an industrial electrical motor. We benchmark our solution using variants of traditional neural networks like feedforward, convolutional, and recurrent networks. We evaluate various design choices of our architecture and compare it to the baselines. We show the domain adaptation capability of our model to learn dynamics just from simulated data by testing it on the raw sensor data. We finally show the effect of signal complexity on the proposed method ability to model temporal dynamics.

Conventional automated test case generation techniques do not scale to modern software systems, as these systems have a large number of requirements that change frequently. In this paper, we present a scalable algorithm, AGenT, that generates test cases to cover maximal requirements. AGenT takes Expressive Decision Tables (EDT), specifying requirements of a system, as input and realises these as multiple Discrete Time Automata (DTAs). AGenT then generates test cases to cover each row of the tables. To improve scalability, it attempts to cover nearer rows (requiring fewer inputs) first, where distance is measured using a novel distance-to-match heuristic. It also maintains information about desirability and predictability of inputs so as to select promising inputs with a higher probability. Although the algorithm has been presented in the context of EDT, it operates on its DTA representation and hence can be applied to any system that is represented as a collection of DTAs like Statemate and Stateflow. In this paper, we describe AGenT in detail and present findings from two experiments that we conducted. We compared AGenT with state-of-the-art algorithms, DRAFT and a random test case generation algorithm, RTG. In the first experiment, AGenT took a maximum of 144 seconds to cover all rows whereas the other two algorithms timed out on many modules. In the second experiment, for a module with 701 rows, AGenT achieved 7% more coverage than DRAFT and 12% more than RTG.

This paper focuses on the quantitative analysis of deep neural networks used in data-driven modeling of induction motor dynamics. With the availability of a large amount of data generated by industrial sensor networks, it is now possible to train deep neural networks. Recently researchers have started exploring the usage of such networks for physics modeling, online control, monitoring, and fault prediction in induction motor operations. We consider the problem of estimating speed and torque from currents and voltages of an induction motor. Neural networks provide quite good performance for this task when analysed from a machine learning perspective using standard metrics. We show, however, that there are some caveats in using machine learning metrics to analyze a neural network model when applied to induction motor problems. Given the mission- critical nature of induction motor operations, the performance of neural networks has to be validated from an electrical engineering point of view. To this end, we evaluate several traditional neural network architectures and recent state of the art architectures on dynamic and quasi-static benchmarks using electrical engineering metrics.

Increasing population indicates that energy demands need to be managed in the residential sector. Prior studies have reflected that the customers tend to reduce a significant amount of energy consumption if they are provided with appliance-level feedback. This observation has increased the relevance of load monitoring in today's tech-savvy world. Most of the previously proposed solutions claim to perform load monitoring without intrusion, but they are not completely non-intrusive. These methods require historical appliance-level data for training the model for each of the devices. This data is gathered by putting a sensor on each of the appliances present in the home which causes intrusion in the building. Some recent studies have proposed that if we frame Non-Intrusive Load Monitoring (NILM) as a multi-label classification problem, the need for appliance-level data can be avoided. In this paper, we propose Multi-label Restricted Boltzmann Machine(ML-RBM) for NILM and report an experimental evaluation of proposed and state-of-the-art techniques.

The advent of multitemporal high resolution data, like the Copernicus Sentinel-2, has enhanced significantly the potential of monitoring the earth's surface and environmental dynamics. In this paper, we present a novel deep learning framework for urban change detection which combines state-of-the-art fully convolutional networks (similar to U-Net) for feature representation and powerful recurrent networks (such as LSTMs) for temporal modeling. We report our results on the recently publicly available bi-temporal Onera Satellite Change Detection (OSCD) Sentinel-2 dataset, enhancing the temporal information with additional images of the same region on different dates. Moreover, we evaluate the performance of the recurrent networks as well as the use of the additional dates on the unseen test-set using an ensemble cross-validation strategy. All the developed models during the validation phase have scored an overall accuracy of more than 95%, while the use of LSTMs and further temporal information, boost the F1 rate of the change class by an additional 1.5%.

In this paper, we consider a territory guarding game involving pursuers, evaders and a target in an environment that contains obstacles. The goal of the evaders is to capture the target, while that of the pursuers is to capture the evaders before they reach the target. All the agents have limited sensing range and can only detect each other when they are in their observation space. We focus on the challenge of effective cooperation between agents of a team. Finding exact solutions for such multi-agent systems is difficult because of the inherent complexity. We present Multi-Agent Pursuer-Evader Learning (MAPEL), a class of algorithms that use spatio-temporal graph representation to learn structured cooperation. The key concept is that the learning takes place in a decentralized manner and agents use situation report updates to learn about the whole environment from each others' partial observations. We use Recurrent Neural Networks (RNNs) to parameterize the spatio-temporal graph. An agent in MAPEL only updates all the other agents if an opponent or the target is inside its observation space by using situation report. We present two methods for cooperation via situation report update: a) Peer-to-Peer Situation Report (P2PSR) and b) Ring Situation Report (RSR). We present a detailed analysis of how these two cooperation methods perform when the number of agents in the game are increased. We provide empirical results to show how agents cooperate under these two methods.

Developing recommendation system for fashion images is challenging due to the inherent ambiguity associated with what criterion a user is looking at. Suggesting multiple images where each output image is similar to the query image on the basis of a different feature or part is one way to mitigate the problem. Existing works for fashion recommendation have used Siamese or Triplet network to learn features between a similar pair and a similar-dissimilar triplet respectively. However, these methods do not provide basic information such as, how two clothing images are similar, or which parts present in the two images make them similar. In this paper, we propose to recommend images by explicitly learning and exploiting part based similarity. We propose a novel approach of learning discriminative features from weakly-supervised data by using visual attention over the parts and a texture encoding network. We show that the learned features surpass the state-of-the-art in retrieval task on DeepFashion dataset. We then use the proposed model to recommend fashion images having an explicit variation with respect to similarity of any of the parts.

We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories. Further, it has been argued that traditional cues used for third person action recognition do not suffice, and egocentric specific features, such as head motion and handled objects have been used for such actions. Unlike the state-of-the-art approaches, we show that a regular two stream Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) architecture, having separate streams for objects and motion, can generalize to all categories of first-person actions. The proposed approach unifies the feature learned by all action categories, making the proposed architecture much more practical. In an important observation, we note that the size of the objects visible in the egocentric videos is much smaller. We show that the performance of the proposed model improves after cropping and resizing frames to make the size of objects comparable to the size of ImageNet's objects. Our experiments on the standard datasets: GTEA, EGTEA Gaze+, HUJI, ADL, UTE, and Kitchen, proves that our model significantly outperforms various state-of-the-art techniques.

Recent times have seen a growing demand for natural language querying (NLQ) interfaces to retrieve information from the structured data sources such as knowledge bases. Using this interface, business users can directly interact with a database without the knowledge of the query language or the data schema. Our earlier work describes a natural language query engine called ATHENA which has several shortcoming around ease of use and compatibility with data stores, formats and flows. In this demonstration paper, we present a tooling framework to address these challenges so that one can instantiate an NLQ system with utmost ease. Our framework makes it easy and practically applicable to all NLIDB scenarios involving different sources of structured data, file formats, and ontologies to enable natural language querying on top of them with minimal human configuration. We present the tool design and the solution to the challenges towards building such a system and demonstrate its applicability in the medical domain.