Search and rescue (SAR) missions require reliable search methods to locate survivors, especially in challenging or inaccessible environments. This is why introducing unmanned aerial vehicles (UAVs) can be of great help to enhance the efficiency of SAR missions while simultaneously increasing the safety of everyone involved in the mission. Motivated by this, we design and experiment with autonomous UAV search for humans in a Mediterranean karst environment. The UAVs are directed using Heat equation-driven area coverage (HEDAC) ergodic control method according to known probability density and detection function. The implemented sensing framework consists of a probabilistic search model, motion control system, and computer vision object detection. It enables calculation of the probability of the target being detected in the SAR mission, and this paper focuses on experimental validation of proposed probabilistic framework and UAV control. The uniform probability density to ensure the even probability of finding the targets in the desired search area is achieved by assigning suitably thought-out tasks to 78 volunteers. The detection model is based on YOLO and trained with a previously collected ortho-photo image database. The experimental search is carefully planned and conducted, while as many parameters as possible are recorded. The thorough analysis consists of the motion control system, object detection, and the search validation. The assessment of the detection and search performance provides strong indication that the designed detection model in the UAV control algorithm is aligned with real-world results.

Scaling pre-training compute has proven effective for achieving mulitlinguality, but does the same hold for test-time scaling? In this work, we introduce MCLM, a multilingual math benchmark featuring competition-level problems in 55 languages. We test three test-time scaling methods-Outcome Reward Modeling (ORM), Process Reward Modeling (ORM), and Budget Forcing (BF)-on both Qwen2.5-1.5B Math and MR1-1.5B, a multilingual LLM we trained for extended reasoning. Our experiments show that using Qwen2.5-1.5B Math with ORM achieves a score of 35.8 on MCLM, while BF on MR1-1.5B attains 35.2. Although "thinking LLMs" have recently garnered significant attention, we find that their performance is comparable to traditional scaling methods like best-of-N once constrained to similar levels of inference FLOPs. Moreover, while BF yields a 20-point improvement on English AIME, it provides only a 1.94-point average gain across other languages-a pattern consistent across the other test-time scaling methods we studied-higlighting that test-time scaling may not generalize as effectively to multilingual tasks. To foster further research, we release MCLM, MR1-1.5B, and evaluation results.

This review explores the integration of deep learning (DL) with full-waveform inversion (FWI) for enhanced seismic imaging and subsurface characterization. It covers FWI and DL fundamentals, geophysical applications (velocity estimation, deconvolution, tomography), and challenges (model complexity, data quality). The review also outlines future research directions, including hybrid, generative, and physics-informed models for improved accuracy, efficiency, and reliability in subsurface property estimation. The synergy between DL and FWI has the potential to transform geophysics, providing new insights into Earth's subsurface.

FWI seeks to achieve a high-resolution model of the subsurface through the application of multi-variate optimization to the seismic inverse problem. Although now a mature technology, FWI has limitations related to the choice of the appropriate solver for the forward problem in challenging environments requiring complex assumptions, and very wide angle and multi-azimuth data necessary for full reconstruction are often not available. Deep Learning techniques have emerged as excellent optimization frameworks. These exist between data and theory-guided methods. Data-driven methods do not impose a wave propagation model and are not exposed to modelling errors. On the contrary, deterministic models are governed by the laws of physics. Application of seismic FWI has recently started to be investigated within Deep Learning. This has focussed on the time-domain approach, while the pseudo-spectral domain has not been yet explored. However, classical FWI experienced major breakthroughs when pseudo-spectral approaches were employed. This work addresses the lacuna that exists in incorporating the pseudo-spectral approach within Deep Learning. This has been done by re-formulating the pseudo-spectral FWI problem as a Deep Learning algorithm for a data-driven pseudo-spectral approach. A novel DNN framework is proposed. This is formulated theoretically, qualitatively assessed on synthetic data, applied to a two-dimensional Marmousi dataset and evaluated against deterministic and time-based approaches. Inversion of data-driven pseudo-spectral DNN was found to outperform classical FWI for deeper and over-thrust areas. This is due to the global approximator nature of the technique and hence not bound by forward-modelling physical constraints from ray-tracing.

Full-Waveform Inversion seeks to achieve a high-resolution model of the subsurface through the application of multi-variate optimization to the seismic inverse problem. Although now a mature technology, FWI has limitations related to the choice of the appropriate solver for the forward problem in challenging environments requiring complex assumptions, and very wide angle and multi-azimuth data necessary for full reconstruction are often not available. Deep Learning techniques have emerged as excellent optimization frameworks. Data-driven methods do not impose a wave propagation model and are not exposed to modelling errors. On the contrary, deterministic models are governed by the laws of physics. Seismic FWI has recently started to be investigated as a Deep Learning framework. Focus has been on the time-domain, while the pseudo-spectral domain has not been yet explored. However, classical FWI experienced major breakthroughs when pseudo-spectral approaches were employed. This work addresses the lacuna that exists in incorporating the pseudo-spectral approach within Deep Learning. This has been done by re-formulating the pseudo-spectral FWI problem as a Deep Learning algorithm for a theory-driven pseudo-spectral approach. A novel Recurrent Neural Network framework is proposed. This is qualitatively assessed on synthetic data, applied to a two-dimensional Marmousi dataset and evaluated against deterministic and time-based approaches. Pseudo-spectral theory-guided FWI using RNN was shown to be more accurate than classical FWI with only 0.05 error tolerance and 1.45\% relative percent-age error. Indeed, this provides more stable convergence, able to identify faults better and has more low frequency content than classical FWI. Moreover, RNN was more suited than classical FWI at edge detection in the shallow and deep sections due to cleaner receiver residuals.

Detecting phishing, spam, fake accounts, data scraping, and other malicious activity in online social networks (OSNs) is a problem that has been studied for well over a decade, with a number of important results. Nearly all existing works on abuse detection have as their goal producing the best possible binary classifier; i.e., one that labels unseen examples as "benign" or "malicious" with high precision and recall. However, no prior published work considers what comes next: what does the service actually do after it detects abuse? In this paper, we argue that detection as described in previous work is not the goal of those who are fighting OSN abuse. Rather, we believe the goal to be selecting actions (e.g., ban the user, block the request, show a CAPTCHA, or "collect more evidence") that optimize a tradeoff between harm caused by abuse and impact on benign users. With this framing, we see that enlarging the set of possible actions allows us to move the Pareto frontier in a way that is unattainable by simply tuning the threshold of a binary classifier. To demonstrate the potential of our approach, we present Predictive Response Optimization (PRO), a system based on reinforcement learning that utilizes available contextual information to predict future abuse and user-experience metrics conditioned on each possible action, and select actions that optimize a multi-dimensional tradeoff between abuse/harm and impact on user experience. We deployed versions of PRO targeted at stopping automated activity on Instagram and Facebook. In both cases our experiments showed that PRO outperforms a baseline classification system, reducing abuse volume by 59% and 4.5% (respectively) with no negative impact to users. We also present several case studies that demonstrate how PRO can quickly and automatically adapt to changes in business constraints, system behavior, and/or adversarial tactics.

The use of autonomous underwater vehicles (AUVs) for surveying, mapping, and inspecting unexplored underwater areas plays a crucial role, where maneuverability and power efficiency are key factors for extending the use of these platforms, making six degrees of freedom (6-DOF) holonomic platforms essential tools. Although Proportional-Integral-Derivative (PID) and Model Predictive Control controllers are widely used in these applications, they often require accurate system knowledge, struggle with repeatability when facing payload or configuration changes, and can be time-consuming to fine-tune. While more advanced methods based on Deep Reinforcement Learning (DRL) have been proposed, they are typically limited to operating in fewer degrees of freedom. This paper proposes a novel DRL-based approach for controlling holonomic 6-DOF AUVs using the Truncated Quantile Critics (TQC) algorithm, which does not require manual tuning and directly feeds commands to the thrusters without prior knowledge of their configuration. Furthermore, it incorporates power consumption directly into the reward function. Simulation results show that the TQC High-Performance method achieves better performance to a fine-tuned PID controller when reaching a goal point, while the TQC Energy-Aware method demonstrates slightly lower performance but consumes 30% less power on average.

Robot-assisted feeding systems enhance the independence of individuals with motor impairments and alleviate caregiver burden. While existing systems predominantly rely on software-based safety features to mitigate risks during unforeseen collisions, this study explores the use of a mechanical fail-safe to improve safety. We designed a breakaway utensil attachment that decouples forces exerted by the robot on the user when excessive forces occur. Finite element analysis (FEA) simulations were performed to predict failure points under various loading conditions, followed by experimental validation using 3D-printed attachments with variations in slot depth and wall loops. To facilitate testing, a drop test rig was developed and validated. Our results demonstrated a consistent failure point at the slot of the attachment, with a slot depth of 1 mm and three wall loops achieving failure at the target force of 65 N. Additionally, the parameters can be tailored to customize the breakaway force based on user-specific factors, such as comfort and pain tolerance. CAD files and utensil assembly instructions can be found here: https://tinyurl.com/rfa-utensil-attachment

Traditional geological mapping methods, which rely on field observations and rock sample analysis, are ine fficient for continuous spatial mapping of geological features such as alteration zones. Deep learning models such as convolutional neural networks (CNNs) have ushered in a transformative era in remote sensing data analysis. CNNs excel in automatically extracting features from image data for classification and regression problems. CNNs have the ability to pinpoint specific mineralogical changes attributed to mineralisation processes by discerning subtle features within remote sensing data. Our methodology involves model training using two distinct sets of training samples generated through ground truth data and a fully automated approach through selective principal component analysis (PCA). We also compare CNNs with conventional machine learning models, including k-nearest neighbours, support vector machines, and multilayer perceptron. Our findings indicate that training with a ground truth-based dataset produces more reliable alteration maps. Additionally, we find that CNNs perform slightly better when compared to conventional machine learning models, which further demonstrates the ability of CNNs to capture spatial patterns in remote sensing data e ffectively. We find that Landsat 9 surpasses Landsat 8 in mapping iron oxide areas when employing the CNNs model trained with ground truth data obtained by field surveys. We also observe that using ASTER data with the CNNs model trained on the ground truth-based dataset produces the most accurate maps for two other important types of alteration zones, argillic and propylitic. This underscores the utility of CNNs in enhancing the e fficiency and precision of geological mapping, particularly in discerning subtle alterations indicative of mineralisation processes, especially those associated with critical metal resources. Introduction Geological maps are traditionally crafted through ground surveys and founded on field observations. They frequently incur inevitable errors due to the lack of spatial continuity of the field observations, thus yielding inaccurate representations (Campbell et al., 2005). Recognising these limitations, geologists have been prompted to seek innovative approaches and e fficient methodologies to accurately map geological features, particularly alteration zones (Kesler, 2007; McCuaig et al., 2010). The utilisation of remote sensing data for alteration mapping emerges as a pivotal technique in regional mineral exploration, enabling the precise spatial identification of alteration zones associated with mineralisation processes (Mohamed et al., 2021).

The aim of this thesis is to extend the applications of the Quantile Regression Forest (QRF) algorithm to handle mixed-frequency and longitudinal data. To this end, standard statistical approaches have been exploited to build two novel algorithms: the Mixed- Frequency Quantile Regression Forest (MIDAS-QRF) and the Finite Mixture Quantile Regression Forest (FM-QRF). The MIDAS-QRF combines the flexibility of QRF with the Mixed Data Sampling (MIDAS) approach, enabling non-parametric quantile estimation with variables observed at different frequencies. FM-QRF, on the other hand, extends random effects machine learning algorithms to a QR framework, allowing for conditional quantile estimation in a longitudinal data setting. The contributions of this dissertation lie both methodologically and empirically. Methodologically, the MIDAS-QRF and the FM-QRF represent two novel approaches for handling mixed-frequency and longitudinal data in QR machine learning framework. Empirically, the application of the proposed models in financial risk management and climate-change impact evaluation demonstrates their validity as accurate and flexible models to be applied in complex empirical settings.