Preterm birth remains a leading cause of neonatal mortality, disproportionately affecting low-resource settings with limited access to advanced neonatal intensive care units (NICUs).Continuous monitoring of infant behavior, such as sleep/awake states and crying episodes, is critical but relies on manual observation or invasive sensors, which are prone to error, impractical, and can cause skin damage. This paper presents a novel, noninvasive, and automated vision-based framework to address this gap. We introduce an embedded monitoring system that utilizes a quantized MobileNet model deployed on a Raspberry Pi for real-time behavioral state detection. When trained and evaluated on public neonatal image datasets, our system achieves state-of-the-art accuracy (91.8% for sleep detection and 97.7% for crying/normal classification) while maintaining computational efficiency suitable for edge deployment. Through comparative benchmarking, we provide a critical analysis of the trade-offs between model size, inference latency, and diagnostic accuracy. Our findings demonstrate that while larger architectures (e.g., ResNet152, VGG19) offer marginal gains in accuracy, their computational cost is prohibitive for real-time edge use. The proposed framework integrates three key innovations: model quantization for memory-efficient inference (68% reduction in size), Raspberry Pi-optimized vision pipelines, and secure IoT communication for clinical alerts. This work conclusively shows that lightweight, optimized models such as the MobileNet offer the most viable foundation for scalable, low-cost, and clinically actionable NICU monitoring systems, paving the way for improved preterm care in resource-constrained environments.

Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR. However, we identify two critical challenges in existing LLM-based SR methods: 1) embedding collapse when incorporating pre-trained collaborative embeddings and 2) catastrophic forgetting of quantized embeddings when utilizing semantic IDs. These issues dampen the model scalability and lead to suboptimal recommendation performance. Therefore, based on LLMs like Llama3-8B-instruct, we introduce a novel SR framework named MME-SID, which integrates multimodal embeddings and quantized embeddings to mitigate embedding collapse. Additionally, we propose a Multimodal Residual Quantized Variational Autoencoder (MM-RQ-VAE) with maximum mean discrepancy as the reconstruction loss and contrastive learning for alignment, which effectively preserve intra-modal distance information and capture inter-modal correlations, respectively. To further alleviate catastrophic forgetting, we initialize the model with the trained multimodal code embeddings. Finally, we fine-tune the LLM efficiently using LoRA in a multimodal frequency-aware fusion manner. Extensive experiments on three public datasets validate the superior performance of MME-SID thanks to its capability to mitigate embedding collapse and catastrophic forgetting. The implementation code and datasets are publicly available for reproduction: https://github.com/Applied-Machine-Learning-Lab/MME-SID.

--Deep learning-based LiDAR odometry is crucial for autonomous driving and robotic navigation, yet its performance under adverse weather, especially snowfall, remains challenging. Existing models struggle to generalize across conditions due to sensitivity to snow-induced noise, limiting real-world use. In this work, we present an unsupervised LiDAR odometry model to close the gap between clear and snowy weather conditions. Our approach focuses on effective denoising to mitigate the impact of snowflake noise and outlier points on pose estimation, while also maintaining computational efficiency for real-time applications. T o achieve this, we introduce a Patch Spatial Measure (PSM) module that evaluates the dispersion of points within each patch, enabling effective detection of sparse and discrete noise. We further propose a Patch Point Weight Predictor (PPWP) to assign adaptive point-wise weights, enhancing their discriminative capacity within local regions. T o support real-time performance, we first apply an intensity threshold mask to quickly suppress dense snowflake clusters near the LiDAR, and then perform multi-modal feature fusion to refine the point-wise weight prediction, improving overall robustness under adverse weather . Our model is trained in clear weather conditions and rigorously tested across various scenarios, including snowy and dynamic. Extensive experimental results confirm the effectiveness of our method, demonstrating robust performance in both clear and snowy weather . This advancement enhances the model's generalizability and paves the way for more reliable autonomous systems capable of operating across a wider range of environmental conditions. IDAR sensors are indispensable in autonomous vehicles and robotics, providing precise 3D spatial data in point cloud form that enables critical tasks such as localization, mapping, and object detection [1], [2].

Logistical demand-supply forecasting that evaluates the alignment between projected supply and anticipated demand, is essential for the efficiency and quality of on-demand food delivery platforms and serves as a key indicator for scheduling decisions. Future order distribution information, which reflects the distribution of orders in on-demand food delivery, is crucial for the performance of logistical demand-supply forecasting. Current studies utilize spatial-temporal analysis methods to model future order distribution information from serious time slices. However, learning future order distribution in online delivery platform is a time-series-insensitive problem with strong randomness. These approaches often struggle to effectively capture this information while remaining efficient. This paper proposes an innovative spatiotemporal learning model that utilizes only two graphs (ongoing and global) to learn future order distribution information, achieving superior performance compared to traditional spatial-temporal long-series methods. The main contributions are as follows: (1) The introduction of ongoing and global graphs in logistical demand-supply pressure forecasting compared to traditional long time series significantly enhances forecasting performance.

Simulating ecohydrological processes is essential for understanding complex environmental systems and guiding sustainable management amid accelerating climate change and human pressures. Process-based models provide physical realism but can suffer from structural rigidity, high computational costs, and complex calibration, while machine learning (ML) methods are efficient and flexible yet often lack interpretability and transferability. We propose a unified three-phase framework that integrates process-based models with ML and progressively embeds them into artificial intelligence (AI) through knowledge distillation. Phase I, behavioral distillation, enhances process models via surrogate learning and model simplification to capture key dynamics at lower computational cost. Phase II, structural distillation, reformulates process equations as modular components within a graph neural network (GNN), enabling multiscale representation and seamless integration with ML models. Phase III, cognitive distillation, embeds expert reasoning and adaptive decision-making into intelligent modeling agents using the Eyes-Brain-Hands-Mouth architecture. Demonstrations for the Samish watershed highlight the framework's applicability to ecohydrological modeling, showing that it can reproduce process-based model outputs, improve predictive accuracy, and support scenario-based decision-making. The framework offers a scalable and transferable pathway toward next-generation intelligent ecohydrological modeling systems, with the potential extension to other process-based domains.

In response to recent FIA regulations reducing Formula 1 team wind tunnel hours (from 320 hours for last-place teams to 200 hours for championship leaders) and strict budget caps of 135 million USD per year, more efficient aerodynamic development tools are needed by teams. Conventional computational fluid dynamics (CFD) simulations, though offering high fidelity results, require large computational resources with typical simulation durations of 8-24 hours per configuration analysis. This article proposes a Physics-Informed Neural Network (PINN) for the fast prediction of Formula 1 front wing aerodynamic coefficients. The suggested methodology combines CFD simulation data from SimScale with first principles of fluid dynamics through a hybrid loss function that constrains both data fidelity and physical adherence based on Navier-Stokes equations. Training on force and moment data from 12 aerodynamic features, the PINN model records coefficient of determination (R-squared) values of 0.968 for drag coefficient and 0.981 for lift coefficient prediction while lowering computational time. The physics-informed framework guarantees that predictions remain adherent to fundamental aerodynamic principles, offering F1 teams an efficient tool for the fast exploration of design space within regulatory constraints.

Disputes between two parties occur in almost all domains such as taxation, insurance, banking, healthcare, etc. The disputes are generally resolved in a specific forum (e.g., consumer court) where facts are presented, points of disagreement are discussed, arguments as well as specific demands of the parties are heard, and finally a human judge resolves the dispute by often favouring one of the two parties. In this paper, we explore the use of large language models (LLMs) as assistants for the human judge to resolve such disputes, as part of our DRAssist system. We focus on disputes from two specific domains -- automobile insurance and domain name disputes. DRAssist identifies certain key structural elements (e.g., facts, aspects or disagreement, arguments) of the disputes and summarizes the unstructured dispute descriptions to produce a structured summary for each dispute. We then explore multiple prompting strategies with multiple LLMs for their ability to assist in resolving the disputes in these domains. In DRAssist, these LLMs are prompted to produce the resolution output at three different levels -- (i) identifying an overall stronger party in a dispute, (ii) decide whether each specific demand of each contesting party can be accepted or not, (iii) evaluate whether each argument by each contesting party is strong or weak. We evaluate the performance of LLMs on all these tasks by comparing them with relevant baselines using suitable evaluation metrics.

Neural architecture search (NAS) is an attractive approach to automate the design of optimized architectures but is constrained by high computational budget, especially when optimizing for multiple, important conflicting objectives. To address this, an adaptive Co-Kriging-assisted multi-fidelity multi-objective NAS algorithm is proposed to further reduce the computational cost of NAS by incorporating a clustering-based local multi-fidelity infill sampling strategy, enabling efficient exploration of the search space for faster convergence. This algorithm is further accelerated by the use of a novel continuous encoding method to represent the connections of nodes in each cell within a generalized cell-based U-Net backbone, thereby decreasing the search dimension (number of variables). Results indicate that the proposed NAS algorithm outperforms previously published state-of-the-art methods under limited computational budget on three numerical benchmarks, a 2D Darcy flow regression problem and a CHASE_DB1 biomedical image segmentation problem. The proposed method is subsequently used to create a wind velocity regression model with application in urban modelling, with the found model able to achieve good prediction with less computational complexity. Further analysis revealed that the NAS algorithm independently identified principles undergirding superior U-Net architectures in other literature, such as the importance of allowing each cell to incorporate information from prior cells.

Marine ecosystems face increasing pressure due to climate change, driving the need for scalable, AI-powered monitoring solutions. This paper examines the rapid emergence of underwater AI as a major research frontier and analyzes the factors that have transformed marine perception from a niche application into a catalyst for AI innovation. We identify three convergent drivers: environmental necessity for ecosystem-scale monitoring, democratization of underwater datasets through citizen science platforms, and researcher migration from saturated terrestrial computer vision domains. Our analysis reveals how unique underwater challenges - turbidity, cryptic species detection, expert annotation bottlenecks, and cross-ecosystem generalization - are driving fundamental advances in weakly supervised learning, open-set recognition, and robust perception under degraded conditions. We survey emerging trends in datasets, scene understanding and 3D reconstruction, highlighting the paradigm shift from passive observation toward AI-driven, targeted intervention capabilities. The paper demonstrates how underwater constraints are pushing the boundaries of foundation models, self-supervised learning, and perception, with methodological innovations that extend far beyond marine applications to benefit general computer vision, robotics, and environmental monitoring.

Modern deep learning developments create new opportunities for 3D mapping technology, scene reconstruction pipelines, and virtual reality development. Despite advances in 3D deep learning technology, direct training of deep learning models on 3D data faces challenges due to the high dimensionality inherent in 3D data and the scarcity of labeled datasets. Structure-from-motion (SfM) and Simultaneous Localization and Mapping (SLAM) exhibit robust performance when applied to structured indoor environments but often struggle with ambiguous features in unstructured environments. These techniques often struggle to generate detailed geometric representations effective for downstream tasks such as rendering and semantic analysis. Current limitations require the development of 3D representation methods that combine traditional geometric techniques with deep learning capabilities to generate robust geometry-aware deep learning models. The dissertation provides solutions to the fundamental challenges in 3D vision by developing geometric deep learning methods tailored for essential tasks such as camera pose estimation, point cloud registration, depth prediction, and 3D reconstruction. The integration of geometric priors or constraints, such as including depth information, surface normals, and equivariance into deep learning models, enhances both the accuracy and robustness of geometric representations. This study systematically investigates key components of 3D vision, including camera pose estimation, point cloud registration, depth estimation, and high-fidelity 3D reconstruction, demonstrating their effectiveness across real-world applications such as digital cultural heritage preservation and immersive VR/AR environments.