This paper explores the assumption that Large Language Models (LLMs) skilled in generation tasks are equally adept as evaluators. We assess the performance of three LLMs and one open-source LM in Question-Answering (QA) and evaluation tasks using the TriviaQA (Joshi et al., 2017) dataset. Results indicate a significant disparity, with LLMs exhibiting lower performance in evaluation tasks compared to generation tasks. Intriguingly, we discover instances of unfaithful evaluation where models accurately evaluate answers in areas where they lack competence, underscoring the need to examine the faithfulness and trustworthiness of LLMs as evaluators. This study contributes to the understanding of "the Generative AI Paradox" (West et al., 2023), highlighting a need to explore the correlation between generative excellence and evaluation proficiency, and the necessity to scrutinize the faithfulness aspect in model evaluations.

This paper describes the design and implementation of a virtual and remote laboratory based on Easy Java Simulations (EJS) and LabVIEW. The main application of this laboratory is to improve the study of sensors in Mobile Robotics, dealing with the problems that arise on the real world experiments. This laboratory allows the user to work from their homes, tele-operating a real robot that takes measurements from its sensors in order to obtain a map of its environment. In addition, the application allows interacting with a robot simulation (virtual laboratory) or with a real robot (remote laboratory), with the same simple and intuitive graphical user interface in EJS. Thus, students can develop signal processing and control algorithms for the robot in simulation and then deploy them on the real robot for testing purposes. Practical examples of application of the laboratory on the inter University Master of Systems Engineering and Automatic Control are presented.

Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment, these methods are usually used to process a large volume of data on a daily basis, imposing a high maintenance cost on medical facilities. In this paper, we introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method to mitigate such challenges. LoGoNet integrates a novel feature extractor within a U-shaped architecture, leveraging Large Kernel Attention (LKA) and a dual encoding strategy to capture both long-range and short-range feature dependencies adeptly. This is in contrast to existing methods that rely on increasing network capacity to enhance feature extraction. This combination of novel techniques in our model is especially beneficial in medical image segmentation, given the difficulty of learning intricate and often irregular body organ shapes, such as the spleen. Complementary, we propose a novel SSL method tailored for 3D images to compensate for the lack of large labeled datasets. The method combines masking and contrastive learning techniques within a multi-task learning framework and is compatible with both Vision Transformer (ViT) and CNN-based models. We demonstrate the efficacy of our methods in numerous tasks across two standard datasets (i.e., BTCV and MSD). Benchmark comparisons with eight state-of-the-art models highlight LoGoNet's superior performance in both inference time and accuracy.

Relevant combinatorial optimization problems (COPs) are often NP-hard. While they have been tackled mainly via handcrafted heuristics in the past, advances in neural networks have motivated the development of general methods to learn heuristics from data. Many approaches utilize a neural network to directly construct a solution, but are limited in further improving based on already constructed solutions at inference time. Our approach, Moco, learns a graph neural network that updates the solution construction procedure based on features extracted from the current search state. This meta training procedure targets the overall best solution found during the search procedure given information such as the search budget. This allows Moco to adapt to varying circumstances such as different computational budgets. Moco is a fully learnable meta optimizer that does not utilize any problem specific local search or decomposition. We test Moco on the Traveling Salesman Problem (TSP) and Maximum Independent Set (MIS) and show that it outperforms other approaches on MIS and is overall competitive on the TSP, especially outperforming related approaches, partially even if they use additional local search.

In recent years, self-supervised learning has excelled for its capacity to learn robust feature representations from unlabelled data. Networks pretrained through self-supervision serve as effective feature extractors for downstream tasks, including Few-Shot Learning. While the evaluation of unsupervised approaches for few-shot learning is well-established in imagery, it is notably absent in acoustics. This study addresses this gap by assessing large-scale self-supervised models' performance in few-shot audio classification. Additionally, we explore the relationship between a model's few-shot learning capability and other downstream task benchmarks. Our findings reveal state-of-the-art performance in some few-shot problems such as SpeechCommandsv2, as well as strong correlations between speech-based few-shot problems and various downstream audio tasks.

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on resource-constrained devices. Our methodology involves training the smaller student model (Neural Network) using the prediction probabilities (as soft labels) of the LLM, which serves as a teacher model. This is achieved through a specialized loss function tailored to learn from the LLM's output probabilities, ensuring that the student model closely mimics the teacher's performance. To validate the performance of the KD approach, we utilized a large dataset, 7T, containing 6,684 student-written responses to science questions and three mathematical reasoning datasets with student-written responses graded by human experts. We compared accuracy with state-of-the-art (SOTA) distilled models, TinyBERT, and artificial neural network (ANN) models. Results have shown that the KD approach has 1% and 4% higher scoring accuracy than ANN and TinyBERT and comparable accuracy to the teacher model. Furthermore, the student model size is 0.02M, 10,000 times smaller in parameters and x10 faster in inferencing than the teacher model and TinyBERT, respectively. The significance of this research lies in its potential to make advanced AI technologies accessible in typical educational settings, particularly for automatic scoring.

The advent of large language models (LLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found that LLMs often resort to shortcuts when performing tasks, creating an illusion of enhanced performance while lacking generalizability in their decision rules. This phenomenon introduces challenges in accurately assessing natural language understanding in LLMs. Our paper provides a concise survey of relevant research in this area and puts forth a perspective on the implications of shortcut learning in the evaluation of language models, specifically for NLU tasks. This paper urges more research efforts to be put towards deepening our comprehension of shortcut learning, contributing to the development of more robust language models, and raising the standards of NLU evaluation in real-world scenarios.

This study investigates the integration of machine learning (ML) and data assimilation (DA) techniques, focusing on implementing surrogate models for Geological Carbon Storage (GCS) projects while maintaining high fidelity physical results in posterior states. Initially, we evaluate the surrogate modeling capability of two distinct machine learning models, Fourier Neural Operators (FNOs) and Transformer UNet (T-UNet), in the context of CO$_2$ injection simulations within channelized reservoirs. We introduce the Surrogate-based hybrid ESMDA (SH-ESMDA), an adaptation of the traditional Ensemble Smoother with Multiple Data Assimilation (ESMDA). This method uses FNOs and T-UNet as surrogate models and has the potential to make the standard ESMDA process at least 50% faster or more, depending on the number of assimilation steps. Additionally, we introduce Surrogate-based Hybrid RML (SH-RML), a variational data assimilation approach that relies on the randomized maximum likelihood (RML) where both the FNO and the T-UNet enable the computation of gradients for the optimization of the objective function, and a high-fidelity model is employed for the computation of the posterior states. Our comparative analyses show that SH-RML offers better uncertainty quantification compared to conventional ESMDA for the case study.

This direction promises a holistic and applied trajectory for Following the core purpose of analyzing and evaluating the influence Computer Engineering education, supported by the outcomes of of a combination of the mentioned innovative teaching our case study, where artifact-centric learning proved effective, methodologies on students' perceptions and experiences, the proposed with 73% of students achieving the highest grade. Self-assessments research question (RQ): RQ: How does a hybrid teaching further corroborated academic excellence, emphasizing students' methodology affect students' perceptions of their learning experiences engagement in skill enhancement and knowledge acquisition.

In this paper we applied data fusion approaches for predicting the final academic performance of university students using multiple-source, multimodal data from blended learning environments. We collected and preprocessed data about first-year university students from different sources: theory classes, practical sessions, on-line Moodle sessions, and a final exam. Our objective was to discover which data fusion approach produced the best results using our data. We carried out experiments by applying four different data fusion approaches and six classification algorithms. The results showed that the best predictions were produced using ensembles and selecting the best attributes approach with discretized data. The best prediction models showed us that the level of attention in theory classes, scores in Moodle quizzes, and the level of activity in Moodle forums were the best set of attributes for predicting students' final performance in our courses.