Related papers: Just in Time to Flip Your Classroom

Most STEM students experience the introductory physics sequence in large-enrollment (N $\gtrsim$ 100 students) classrooms, led by one lecturer and supported by a few teaching assistants. This work describes methods and principles we used to…

Flipped classrooms promote active learning by having students engage with materials independently before class, allowing in-class time for collaborative problem-solving. During this pre-class phase, asynchronous online discussions help…

Git and GitHub are common tools for keeping track of multiple versions of data analytic content, which allow for more than one person to simultaneously work on a project. GitHub Classroom aims to provide a way for students to work on and…

Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback at scale, current studies lack clear methodologies for providing Just-in-Time (JiT)…

The increasing number and scale of federated learning (FL) jobs necessitates resource efficient scheduling and management of aggregation to make the economics of cloud-hosted aggregation work. Existing FL research has focused on the design…

COVID-19 has significantly affected universities, forcing many courses to be delivered entirely online. As countries bring the pandemic under control, a potential way to safely resume some face-to-face teaching is the synchronous hybrid…

Federated learning aims to learn a global model collaboratively while the training data belongs to different clients and is not allowed to be exchanged. However, the statistical heterogeneity challenge on non-IID data, such as class…

Artificial Intelligence and especially Large Language Models (LLM), such as ChatGPT has revolutionized the way educators work. The results we get from LLMs depend on how we ask them to help us. The process and the technique behind an…

In high-dimensional robotic path planning, traditional sampling-based methods often struggle to efficiently identify both feasible and optimal paths in complex, multi-obstacle environments. This challenge is intensified in robotic…

Recent work has shown that Just-In-Time (JIT) compilation can introduce timing side-channels to constant-time programs, which would otherwise be a principled and effective means to counter timing attacks. In this paper, we propose a novel…

The rise of AI, especially Large Language Models, presents challenges and opportunities to integrate such technology into the classroom. AI has the potential to revolutionize education by helping teaching staff with various tasks, such as…

Between 2017 and 2019, a standard Linear Algebra course from Instituto Superior T\'ecnico, University of Lisbon, used virtual learning content, mainly videos and formative assessment, delivered at the institution's MOOC platform to support…

Pretraining on human corpus and then finetuning in a simulator has become a standard pipeline for training a goal-oriented dialogue agent. Nevertheless, as soon as the agents are finetuned to maximize task completion, they suffer from the…

Large language models promise a broad set of functions, but when not given a specific objective, they default to generic results. We demonstrate that inferring the user's in-the-moment objective, then rapidly optimizing for that singular…

The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient…

We propose Gradient Inversion Transcript (GIT), a novel generative approach for reconstructing training data from leaked gradients. GIT employs a generative attack model, whose architecture is tailored to align with the structure of the…

In these lectures I give an introduction to the time-dependent approach to inverse scattering, that has been developed recently. The aim of this approach is to solve various inverse scattering problems with time-dependent methods that…

The digital age is changing the role of educators and pushing for a paradigm shift in the education system as a whole. Growing demand for general and specialized education inside and outside classrooms is at the heart of this rising trend.…

We investigate video transforms that result in class-homogeneous label-transforms. These are video transforms that consistently maintain or modify the labels of all videos in each class. We propose a general approach to discover invariant…

This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to…