Related papers: Understanding Distributed Tutorship in Online Lang…
Is more data always better to train vision-and-language models? We study knowledge transferability in multi-modal tasks. The current tendency in machine learning is to assume that by joining multiple datasets from different tasks their…
Heuristic and scaffolded teacher-student dialogues are widely regarded as critical for fostering students' higher-order thinking and deep learning. However, large language models (LLMs) currently face challenges in generating pedagogically…
With the rapid growth in the volume of data sets, models, and devices in the domain of deep learning, there is increasing attention on large-scale distributed deep learning. In contrast to traditional distributed deep learning, the…
Recent advances in large language models (LLMs) demonstrate their potential as educational tutors. However, different tutoring strategies benefit different student personalities, and mismatches can be counterproductive to student outcomes.…
Conversation is like an intricate partner dance and behavioral convergence, or the similarity in observable behaviors of partners over time, can lead to shared understanding, changed beliefs and increased rapport. This article describes a…
The primary aim of this study in this paper aside from presenting student preference survey data and analytics data with relation to learning videos, is to address the attention span issues with our cohort of Information Technology students…
Online learning with streaming data in a distributed and collaborative manner can be useful in a wide range of applications. This topic has been receiving considerable attention in recent years with emphasis on both single-task and…
Multimodal learning has seen remarkable progress, particularly with the emergence of large-scale pre-training across various modalities. However, most current approaches are built on the assumption of a deterministic, one-to-one alignment…
One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage previously acquired knowledge to converge faster on the current task. Usually this is done through fine-tuning, where an implicit…
The adaption of multilingual pre-trained LLMs into eloquent and helpful assistants is essential to facilitate their use across different language regions. In that spirit, we are the first to conduct an extensive study of the performance of…
Most AI-based educational tools today adopt a one-on-one tutoring paradigm, pairing a single LLM with a single learner. Yet decades of learning science research suggest that multi-party interaction -- through peer modeling, co-construction,…
The teacher-student framework, prevalent in semi-supervised semantic segmentation, mainly employs the exponential moving average (EMA) to update a single teacher's weights based on the student's. However, EMA updates raise a problem in that…
Whenever students use any drilling system the question arises how much of their learning is meaningful learning vs memorisation through repetition or rote learning. Although both types of learning have their place in an educational system…
Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. We employ a teacher-student framework and propose a novel…
When adopting the role of a teacher in learning-by-teaching environments, students often struggle to engage in knowledge-building activities, such as providing explanations and addressing misconceptions. Instead, they frequently default to…
In increasingly multicultural and multilingual societies, foreign language learning has become essential not only for communication but also for social cohesion and professional advancement. Distance education has emerged as a flexible and…
Providing consistent, individualized feedback to teachers on their instruction can improve student learning outcomes. Such feedback can especially benefit novice instructors who teach on online platforms and have limited access to…
We analyze a dataset of 51 current (2019-2020) Distributed Systems syllabi from top Computer Science programs, focusing on finding the prevalence and context in which topics related to performance are being taught in these courses. We also…
The scope of this paper was to find out how the students in Computer Science perceive different teaching styles and how the teaching style impacts the learning desire and interest in the course. To find out, we designed and implemented an…
Peer-led team learning (PLTL) is a model for teaching STEM courses where small student groups meet periodically to collaboratively discuss coursework. Automatic analysis of PLTL sessions would help education researchers to get insight into…