Ostfalia University of Applied Sciences Abstract: This research examines the impact of robotics groups in higher education, focusing on how these activities influence the development of transversal skills and academic motivation. While robotics goes beyond just technical knowledge, participation in these groups has been observed to significantly improve skills such as teamwork, creativity, and problem-solving. The study, conducted with the UruBots group, shows that students involved in robotics not only reinforce their theoretical knowledge but also increase their interest in research and academic commitment. These results highlight the potential of educational robotics to transform the learning experience by promoting active and collaborative learning. This work lays the groundwork for future research on how robotics can continue to enhance higher education and motivate students in their academic and professional careers.

Graphons are continuous models that represent the structure of graphs and allow the generation of graphs of varying sizes. We propose Scalable Implicit Graphon Learning (SIGL), a scalable method that combines implicit neural representations (INRs) and graph neural networks (GNNs) to estimate a graphon from observed graphs. Unlike existing methods, which face important limitations like fixed resolution and scalability issues, SIGL learns a continuous graphon at arbitrary resolutions. GNNs are used to determine the correct node ordering, improving graph alignment. Furthermore, we characterize the asymptotic consistency of our estimator, showing that more expressive INRs and GNNs lead to consistent estimators. We evaluate SIGL in synthetic and real-world graphs, showing that it outperforms existing methods and scales effectively to larger graphs, making it ideal for tasks like graph data augmentation.

One of the main challenges of federated learning (FL) is handling non-independent and identically distributed (non-IID) client data, which may occur in practice due to unbalanced datasets and use of different data sources across clients. Knowledge sharing and model personalization are key strategies for addressing this issue. Clustered federated learning is a class of FL methods that groups clients that observe similarly distributed data into clusters, such that every client is typically associated with one data distribution and participates in training a model for that distribution along their cluster peers. In this paper, we present a unified Bayesian framework for clustered FL which associates clients to clusters. Then we propose several practical algorithms to handle the, otherwise growing, data associations in a way that trades off performance and computational complexity. This work provides insights on client-cluster associations and enables client knowledge sharing in new ways. The proposed framework circumvents the need for unique client-cluster associations, which is seen to increase the performance of the resulting models in a variety of experiments.

We introduce KANICE (Kolmogorov-Arnold Networks with Interactive Convolutional Elements), a novel neural architecture that combines Convolutional Neural Networks (CNNs) with Kolmogorov-Arnold Network (KAN) principles. KANICE integrates Interactive Convolutional Blocks (ICBs) and KAN linear layers into a CNN framework. This leverages KANs' universal approximation capabilities and ICBs' adaptive feature learning. KANICE captures complex, non-linear data relationships while enabling dynamic, context-dependent feature extraction based on the Kolmogorov-Arnold representation theorem. We evaluated KANICE on four datasets: MNIST, Fashion-MNIST, EMNIST, and SVHN, comparing it against standard CNNs, CNN-KAN hybrids, and ICB variants. KANICE consistently outperformed baseline models, achieving 99.35% accuracy on MNIST and 90.05% on the SVHN dataset. Furthermore, we introduce KANICE-mini, a compact variant designed for efficiency. A comprehensive ablation study demonstrates that KANICE-mini achieves comparable performance to KANICE with significantly fewer parameters. KANICE-mini reached 90.00% accuracy on SVHN with 2,337,828 parameters, compared to KANICE's 25,432,000. This study highlights the potential of KAN-based architectures in balancing performance and computational efficiency in image classification tasks. Our work contributes to research in adaptive neural networks, integrates mathematical theorems into deep learning architectures, and explores the trade-offs between model complexity and performance, advancing computer vision and pattern recognition. The source code for this paper is publicly accessible through our GitHub repository (https://github.com/m-ferdaus/kanice).

Optimal power flow (OPF) has been used for real-time grid operations. Prior efforts demonstrated that utilizing flexibility from dynamic topologies will improve grid efficiency. However, this will convert the linear OPF into a mixed-integer linear programming network-reconfigured OPF (NR-OPF) problem, substantially increasing the computing time. Thus, a machine learning (ML)-based approach, particularly utilizing graph neural network (GNN), is proposed to accelerate the solution process. The GNN model is trained offline to predict the best topology before entering the optimization stage. In addition, this paper proposes an offline pre-ML filter layer to reduce GNN model size and training time while improving its accuracy. A fast online post-ML selection layer is also proposed to analyze GNN predictions and then select a subset of predicted NR solutions with high confidence. Case studies have demonstrated superior performance of the proposed GNN-accelerated NR-OPF method augmented with the proposed pre-ML and post-ML layers.

This study investigates the risks of exposing confidential chemical structures when machine learning models trained on these structures are made publicly available. We use membership inference attacks, a common method to assess privacy that is largely unexplored in the context of drug discovery, to examine neural networks for molecular property prediction in a black-box setting. Our results reveal significant privacy risks across all evaluated datasets and neural network architectures. Combining multiple attacks increases these risks. Molecules from minority classes, often the most valuable in drug discovery, are particularly vulnerable. We also found that representing molecules as graphs and using message-passing neural networks may mitigate these risks. We provide a framework to assess privacy risks of classification models and molecular representations. Our findings highlight the need for careful consideration when sharing neural networks trained on proprietary chemical structures, informing organisations and researchers about the trade-offs between data confidentiality and model openness.

RAG systems consist of multiple modules to work together. However, these modules are usually separately trained. We argue that a system like RAG that incorporates multiple modules should be jointly optimized to achieve optimal performance. To demonstrate this, we design a specific pipeline called SmartRAG that includes a policy network and a retriever. The policy network can serve as 1) a decision maker that decides when to retrieve, 2) a query rewriter to generate a query most suited to the retriever, and 3) an answer generator that produces the final response with/without the observations. We then propose to jointly optimize the whole system using a reinforcement learning algorithm, with the reward designed to encourage the system to achieve the best performance with minimal retrieval cost. When jointly optimized, all the modules can be aware of how other modules are working and thus find the best way to work together as a complete system. Empirical results demonstrate that the jointly optimized SmartRAG can achieve better performance than separately optimized counterparts. Although large language models(LLMs) (Chowdhery et al., 2023; Touvron et al., 2023; Chung et al., 2024) have demonstrated exceptional capabilities across various domains, addressing knowledgerelated issues beyond model parameters remains a challenging task (Mallen et al., 2023b; Min et al., 2023). Retrieval-augmentation generation(RAG) effectively enhances model performance in these scenarios by retrieving additional information from external tools (Ram et al., 2023). RAG systems usually consist of multiple modules including at least a retriever and a generator. Some systems may have other modules like a reranker (Glass et al., 2022), a decision maker deciding when to retrieve (Jeong et al., 2024; Wang et al., 2023a), a query rewriter (Ma et al., 2023; Tan et al., 2024) or a verifier (Lewis et al., 2020; Izacard et al., 2023). These modules are often hand-designed and separately optimized. One of the issues is that the golden answer of the intermediate modules are usually not accessible. What is worse, sometimes the golden answer is model-dependent or retriever-dependent. For example, Asai et al. (2024) uses the result of GPT4 (Achiam et al., 2023) as the ground truth for the decision maker, which can be suboptimal.

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful, biased and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. Extensive experiments across various tasks and models reveal clear distinctions in the causal distributions between normal behavior and misbehavior, enabling the development of accurate, lightweight detectors for a variety of misbehavior detection tasks. Large language models (LLMs) demonstrate advanced capabilities in mimicking human language and styles for diverse applications (OpenAI, 2023), from literary creation (Yuan et al., 2022) to code generation (Li et al., 2023; Wang et al., 2023b). At the same time, they have shown the potential to misbehave in various ways, raising serious concerns about their use in critical real-world applications. First, LLMs can inadvertently produce untruthful responses, fabricating information that may be plausible but entirely fictitious, thus misleading users or misrepresenting facts (Rawte et al., 2023). Second, LLMs can be exploited for malicious purposes, such as through jailbreak attacks (Liu et al., 2024; Zou et al., 2023b; Zeng et al., 2024), where the model's safety mechanisms are bypassed to produce harmful outputs. Third, the generation of toxic responses such as insulting or offensive content remains a significant concern (Wang & Chang, 2022). Lastly, biased responses, which can appear as discriminatory or prejudiced remarks, are especially troubling as they have the potential to reinforce stereotypes and undermine societal efforts toward equality and inclusivity (Stanovsky et al., 2019; Zhao et al., 2018). Numerous attempts have been made to detect LLM misbehavior (Pacchiardi et al., 2023; Robey et al., 2024; Sap et al., 2020; Caselli et al., 2021). However, existing approaches often face two significant limitations. First, they tend to focus on a single type of misbehavior, which reduces the overall effectiveness of each method and requires the integration of multiple systems to comprehensively address the diverse forms of misbehavior. Second, many methods rely on analyzing the model's responses, which can be inefficient or even ineffective, particularly for longer outputs. Additionally, they are often vulnerable to adaptive adversarial attacks (Sato et al., 2018; Hartvigsen et al., 2022). As a result, there is an urgent need for more general and robust misbehavior detection methods capable of identifying (and mitigating) the full range of LLM misbehavior. In this work, we introduce LLMScan, an approach designed to address this critical need.

In this light, data workloads seem to Chaining functions for longer workloads is a key use case for FaaS be a natural fit for Function-as-a-Service (FaaS) platforms designed platforms in data applications. However, modern data pipelines to efficiently handle bursty, functional, and event-driven tasks. Unfortunately, differ significantly from typical serverless use cases (e.g., webhooks existing FaaS runtimes fall short in practice as they and microservices); this makes it difficult to retrofit existing pipeline were primarily designed to support the execution of many simple, frameworks due to structural constraints. In this paper, we describe independent functions that produce small outputs. Although popular these limitations in detail and introduce bauplan, a novel FaaS FaaS platforms (e.g., AWS Lambda [5], Azure Functions [17], and programming model and serverless runtime designed for data practitioners. OpenWhisk [4]) have added support for function chaining, their bauplan enables users to declaratively define functional capabilities fall short for data pipelines. It is therefore not surprising Directed Acyclic Graphs (DAGs) along with their runtime environments, that widely used data engineering frameworks (e.g., Airflow [1], which are then efficiently executed on cloud-based workers. Prefect [19], and Luigi [23]) lack native integration with serverless We show that bauplan achieves both better performance and a runtimes.

Enabling robots to autonomously navigate unknown, complex, dynamic environments and perform diverse tasks remains a fundamental challenge in developing robust autonomous physical agents. These agents must effectively perceive their surroundings while leveraging world knowledge for decision-making. Although recent approaches utilize vision-language and large language models for scene understanding and planning, they often rely on offline processing, offboard compute, make simplifying assumptions about the environment and perception, limiting real-world applicability. We present a novel framework for real-time onboard autonomous navigation in unknown environments that change over time by integrating multi-level abstraction in both perception and planning pipelines. Our system fuses data from multiple onboard sensors for localization and mapping and integrates it with open-vocabulary semantics to generate hierarchical scene graphs from continuously updated semantic object map. The LLM-based planner uses these graphs to create multi-step plans that guide low-level controllers in executing navigation tasks specified in natural language. The system's real-time operation enables the LLM to adjust its plans based on updates to the scene graph and task execution status, ensuring continuous adaptation to new situations or when the current plan cannot accomplish the task, a key advantage over static or rule-based systems. We demonstrate our system's efficacy on a quadruped navigating dynamic environments, showcasing its adaptability and robustness in diverse scenarios.