Related papers: Classroom Technology Deployment Matrix: A Planning…
Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) trained on a given instruction dataset. Curriculum learning as a typical data organization strategy has shown preliminary effectiveness in…
Integrating artificial intelligence (AI) into software engineering can transform traditional practices by enhancing efficiency, accuracy, and innovation. This study explores using ChatGPT, an advanced AI language model, to enhance UML class…
To effectively manage Technical Debt (TD), we need reliable means to quantify it. We conducted a Systematic Mapping Study (SMS) where we identified TD quantification approaches that focus on different aspects of TD. Some approaches base the…
Technology-Enhanced Formative Assessment (TEFA) is a pedagogy for teaching with classroom response technology. Teacher Learning of TEFA is a five-year research project studying teacher change, in the context of an intensive professional…
Multi-task learning (MTL) is a methodology that aims to improve the general performance of estimation and prediction by sharing common information among related tasks. In the MTL, there are several assumptions for the relationships and…
The study is conducted to evaluate the job satisfaction among the administrative and teaching faculties in higher educational institutions. Many researchers have conducted studies to evaluate differences in job perception between teaching…
Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…
Prediction tasks about students have practical significance for both student and college. Making multiple predictions about students is an important part of a smart campus. For instance, predicting whether a student will fail to graduate…
When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what…
Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approaches are based on the Mean Teacher (MT) structure, which…
Emergence of latest technologies has diverted the focus of people form Computer-Supported Collaborative Learning (CSCL) to mobile supported collaborative learning. MCL is highly demanded in educational organizations to substantiate the…
Offloading computational tasks from resource-constrained devices to resource-abundant peers constitutes a critical paradigm for collaborative computing. Within this context, accurate trust evaluation of potential collaborating devices is…
Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated…
The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization. However, this assumption oversimplifies the real…
We introduce Time-Conditioned Contraction Matching (TCCM), a novel method for semi-supervised anomaly detection in tabular data. TCCM is inspired by flow matching, a recent generative modeling framework that learns velocity fields between…
This study examines the integration of digital collaborative tools and structured peer evaluation in the Machine Learning for Health master's program, through the redesign of a Biomedical Image Processing course over two academic years. The…
Professional societies often publish curriculum guidelines to help programs align their content to international standards. In Computer Science, the primary standard is published by ACM and IEEE and provide detailed guidelines for what…
The application of the Internet in the field of education is becoming more and more popular, and a large amount of educational data is generated in the process. How to effectively use these data has always been a key issue in the field of…
Recent advancements in Large Language Models (LLMs) have spurred numerous attempts to apply these technologies to embodied tasks, particularly focusing on high-level task planning and task decomposition. To further explore this area, we…
While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer…