Related papers: Enhancing Science Literacy through Cognitive Confl…

Introducing gravitational physics at high school provides educational means for bridging the gap between the image of science held by students and science itself. Natural language is fundamental in this learning. It engages students in…

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Knowledge graph completion (KGC) focuses on identifying missing triples in a knowledge graph (KG) , which is crucial for many downstream applications. Given the rapid development of large language models (LLMs), some LLM-based methods are…

The modern engineering landscape increasingly requires a range of skills to successfully integrate complex systems. Project-based learning is used to help students build professional skills. However, it is typically applied to small teams…

The evolution of science education is a dynamic process driven by advances in pedagogy, technology, and especially, our understanding of how students learn. Educators are exploring innovative teaching and learning methodologies such as…

While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Catastrophic Forgetting (GCF). We observe…

This is a report on a qualitative study of students' learning where a physics computer simulation session is used to supplement lectures on the topic. Drawing on phenomenography as the analytical framework, the students' learning-focuses…

Individual teaching is among the most successful ways to impart knowledge. Yet, this method is not always feasible due to large numbers of students per educator. Quantum computing serves as a prime example facing this issue, due to the hype…

With the proliferation of large language model (LLM) applications since 2022, their use in education has sparked both excitement and concern. Recent studies consistently highlight students' (mis)use of LLMs can hinder learning outcomes.…

Learning-based congestion control (CC), including Reinforcement-Learning, promises efficient CC in a fast-changing networking landscape, where evolving communication technologies, applications and traffic workloads pose severe challenges to…

Despite the prevalence of physics education research literature related to problem solving, recent studies have illustrated that opportunities for ``authentic'' problem solving -- conceptualized as making decisions with limited information…

Project-Based Learning (PBL) involves a variety of highly correlated multimodal data, making it a vital educational approach within STEM disciplines. With the rapid development of multimodal large language models (MLLMs), researchers have…

In multi-task learning (MTL), gradient conflict poses a significant challenge. Effective methods for addressing this problem, including PCGrad, CAGrad, and GradNorm, in their original implementations are computationally demanding, which…

Projects and Practices in Physics (P$^3$) is an introductory physics class at Michigan State University that replaces lectures with a problem based learning environment. To promote the development of group based practices, students all…

Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a controllable trajectory. This provides a simple and flexible way to inject external constraints…

Measuring learning progress is essential for curiosity-driven exploration in reinforcement learning, but widely used signals such as prediction error often fail to distinguish meaningful, learnable patterns from random noise. This paper…

Generative models have demonstrated human-level proficiency in various benchmarks across domains like programming, natural sciences, and general knowledge. Despite these promising results on competitive benchmarks, they still struggle with…

With the continuous advancement of reasoning abilities in Large Language Models (LLMs), their application to scientific reasoning tasks has gained significant research attention. Current research primarily emphasizes boosting LLMs'…

Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we…

It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated knowledge prompting,…