Related papers: Generating Language Corrections for Teaching Physi…
For an AI's training process to successfully impart a desired goal, it is important that the AI does not attempt to resist the training. However, partially learned goals will often incentivize an AI to avoid further goal updates, as most…
Teaching systems physical tasks is a long standing goal in HCI, yet most prior work has focused on non collaborative physical activities. Collaborative tasks introduce added complexity, requiring systems to infer users assumptions about…
Automated feedback generation for introductory programming assignments is useful for programming education. Most works try to generate feedback to correct a student program by comparing its behavior with an instructor's reference program on…
As robots become more prevalent, optimizing their design for better performance and efficiency is becoming increasingly important. However, current robot design practices overlook the impact of perception and design choices on a robot's…
This letter presents a physical human-robot interaction scenario in which a robot guides and performs the role of a teacher within a defined dance training framework. A combined cognitive and physical feedback of performance is proposed for…
Access to high-quality education at scale is limited by the difficulty of providing student feedback on open-ended assignments in structured domains like computer programming, graphics, and short response questions. This problem has proven…
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…
Despite the precision and adaptiveness of generative AI (GAI)-powered feedback provided to students, existing practice and literature might ignore how usage patterns impact student learning. This study examines the heterogeneous effects of…
In this paper we address feedback strategies for an autonomous virtual trainer. First, a pilot study was conducted to identify and specify feedback strategies for assisting participants in performing a given task. The task involved sorting…
Generative AI has the potential to transform personalization and accessibility of education. However, it raises serious concerns about accuracy and helping students become independent critical thinkers. In this study, we designed a helpful…
Computer science class enrollments have rapidly risen in the past decade. With current class sizes, standard approaches to grading and providing personalized feedback are no longer possible and new techniques become both feasible and…
Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training…
In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e.g.,…
As AI writing tools evolve from fixing surface errors to creating language with writers, new capabilities raise concerns about negative impacts on student writers, such as replacing their voices and undermining critical thinking skills. To…
The recent advancement of Artificial Intelligence Generated Content (AIGC) has led to significant strides in modeling human interaction, particularly in the context of multimodal dialogue. While current methods impressively generate…
We investigate whether naturalistic emotional human feedback can be directly exploited as a reward signal for training artificial agents via interactive human-in-the-loop reinforcement learning. To answer this question, we devise an…
This study explores how generative artificial intelligence, specifically ChatGPT, can assist in the evaluation of laboratory reports in Experimental Physics. Two interaction modalities were implemented: an automated API-based evaluation and…
This study explores how generative artificial intelligence, specifically ChatGPT, can assist in the evaluation of laboratory reports in Experimental Physics. Two interaction modalities were implemented: an automated API-based evaluation and…
Kanji script writing is a skill that is often introduced to novice Japanese foreign language students for achieving Japanese writing mastery, but often poses difficulties to students with primarily English fluency due to their its vast…
We introduce a novel formulation for incorporating visual feedback in controlling robots. We define a generative model from actions to image observations of features on the end-effector. Inference in the model allows us to infer the robot…