相关论文: Context, input and process as critical elements fo…

Online learning is becoming increasingly popular, whether for convenience, to accommodate work hours, or simply to have the freedom to study from anywhere. Especially, during the Covid-19 pandemic, it has become the only viable option for…

Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not…

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Computer-based learning platforms (CBLPs) have become a common medium in schools, transforming how students learn and interact with educational content. However, researchers still lack adequate tools to address the diverse set of challenges…

In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Recent advances have attempted to improve model performance through principles derived from…

This paper is based on the study of existing literature, highlights the current state of the work proposed to implement technically enhanced learning. Technology developments and network infrastructure improvements, specifically the world…

The growth of Internet has led to new approaches for distance education. The main mechanisms involved in this process are distance learning and distance evaluation. Distance learning have multiple forms, from browsing and finding…

Educational Institutions have an essential role in promoting the teaching and learning process, within universities, colleges, and communities. Due to the recent coronavirus COVID 19 pandemic, many educational institutions adopted hybrid…

Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing. Despite these advances, a…

The COVID-19 outbreak has stimulated the interest in the proposal of novel epidemiological models to predict the course of the epidemic so as to help planning effective control strategies. In particular, in order to properly interpret the…

Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints that expert agents adhere to, based on their demonstration data. As an emerging research topic, ICRL has received considerable attention in…

Residential colleges and universities face unique challenges in providing in-person instruction during the COVID-19 pandemic. Administrators are currently faced with decisions about whether to open during the pandemic and what modifications…

Understanding learner emotions in online education is critical for improving engagement and personalized instruction. While prior work in emotion recognition has explored multimodal fusion and temporal modeling, existing methods often rely…

In the training process of Deep Reinforcement Learning (DRL), agents require repetitive interactions with the environment. With an increase in training volume and model complexity, it is still a challenging problem to enhance data…

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

Emotion recognition in conversation (ERC) aims to detect the emotion label for each utterance. Motivated by recent studies which have proven that feeding training examples in a meaningful order rather than considering them randomly can…

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety…

The COVID-19 pandemic has forced schools and universities to adapt to remote learning, and online gaming has emerged as a tool for education. Educational games can make learning fun and engaging, help students develop important skills like…

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…

This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and…