Tiffany D. Do

Arijit Chakma, Peng He, Honglu Liu et al.

Developing expertise in diagnostic reasoning requires practice with diverse student artifacts, yet privacy regulations prohibit sharing authentic student work for teacher professional development (PD) at scale. We present DrawSim-PD, the first generative framework that simulates NGSS-aligned, student-like science drawings exhibiting controllable pedagogical imperfections to support teacher training. Central to our approach are apability profiles--structured cognitive states encoding what students at each performance level can and cannot yet demonstrate. These profiles ensure cross-modal coherence across generated outputs: (i) a student-like drawing, (ii) a first-person reasoning narrative, and (iii) a teacher-facing diagnostic concept map. Using 100 curated NGSS topics spanning K-12, we construct a corpus of 10,000 systematically structured artifacts. Through an expert-based feasibility evaluation, K--12 science educators verified the artifacts' alignment with NGSS expectations (>84% positive on core items) and utility for interpreting student thinking, while identifying refinement opportunities for grade-band extremes. We release this open infrastructure to overcome data scarcity barriers in visual assessment research.

Alec G. Moore, Tiffany D. Do, Nayan N. Chawla et al.

In recent years, numerous researchers have begun investigating how virtual reality (VR) tracking and interaction data can be used for a variety of machine learning purposes, including user identification, predicting cybersickness, and estimating learning gains. One constraint for this research area is the dearth of open datasets. In this paper, we present a new open dataset captured with our VR-based Full-scale Assembly Simulation Testbed (FAST). This dataset consists of data collected from 108 participants (50 females, 56 males, 2 non-binary) learning how to assemble two distinct full-scale structures in VR. In addition to explaining how the dataset was collected and describing the data included, we discuss how the dataset may be used by future researchers.

Vishnu Menon, Andy Cherney, Elizabeth B. Cloude et al.

This study examined whether embedding LLM-guided reflection prompts in an interactive AI-generated podcast improved learning and user experience compared to a version without prompts. Thirty-six undergraduates participated, and while learning outcomes were similar across conditions, reflection prompts reduced perceived attractiveness, highlighting a call for more research on reflective interactivity design.

Steven Abreu, Tiffany D. Do, Karan Ahuja et al.

Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and evaluating these annotations. First, we used a prompt-engineered large language model (LLM) to generate context-aware action suggestions and identified over 18,000 action suggestions. While these synthetic action suggestions are valuable, the inherent limitations of LLMs necessitate human evaluation. To ensure high-quality and user-centered recommendations, we conducted a large-scale human annotation study that provides grounding in human preferences for all of PARSE-Ego4D. We analyze the inter-rater agreement and evaluate subjective preferences of participants. Based on our synthetic dataset and complete human annotations, we propose several new tasks for action suggestions based on ego-centric videos. We encourage novel solutions that improve latency and energy requirements. The annotations in PARSE-Ego4D will support researchers and developers who are working on building action recommendation systems for augmented and virtual reality systems.

Tiffany D. Do, Seong Ioi Wang, Dylan S. Yu et al.

League of Legends (LoL) is the most widely played multiplayer online battle arena (MOBA) game in the world. An important aspect of LoL is competitive ranked play, which utilizes a skill-based matchmaking system to form fair teams. However, players' skill levels vary widely depending on which champion, or hero, that they choose to play as. In this paper, we propose a method for predicting game outcomes in ranked LoL games based on players' experience with their selected champion. Using a deep neural network, we found that game outcomes can be predicted with 75.1% accuracy after all players have selected champions, which occurs before gameplay begins. Our results have important implications for playing LoL and matchmaking. Firstly, individual champion skill plays a significant role in the outcome of a match, regardless of team composition. Secondly, even after the skill-based matchmaking, there is still a wide variance in team skill before gameplay begins. Finally, players should only play champions that they have mastered, if they want to win games.

Tiffany D. Do, Joseph J. LaViola, Ryan P. McMahan

Depth perception of objects can greatly affect a user's experience of an augmented reality (AR) application. Many AR applications require depth matching of real and virtual objects and have the possibility to be influenced by depth cues. Color and luminance are depth cues that have been traditionally studied in two-dimensional (2D) objects. However, there is little research investigating how the properties of three-dimensional (3D) virtual objects interact with color and luminance to affect depth perception, despite the substantial use of 3D objects in visual applications. In this paper, we present the results of a paired comparison experiment that investigates the effects of object shape, fidelity, color, and luminance on depth perception of 3D objects in handheld mobile AR. The results of our study indicate that bright colors are perceived as nearer than dark colors for a high-fidelity, simple 3D object, regardless of hue. Additionally, bright red is perceived as nearer than any other color. These effects were not observed for a low-fidelity version of the simple object or for a more-complex 3D object. High-fidelity objects had more perceptual differences than low-fidelity objects, indicating that fidelity interacts with color and luminance to affect depth perception. These findings reveal how the properties of 3D models influence the effects of color and luminance on depth perception in handheld mobile AR and can help developers select colors for their applications.

Tiffany D. Do, Dylan S. Yu, Salman Anwer et al.

League of Legends (LoL), one of the most widely played computer games in the world, has over 140 playable characters known as champions that have highly varying play styles. However, there is not much work on providing champion recommendations to a player in LoL. In this paper, we propose that a recommendation system based on a collaborative filtering approach using singular value decomposition provides champion recommendations that players enjoy. We discuss the implementation behind our recommendation system and also evaluate the practicality of our system using a preliminary user study. Our results indicate that players significantly preferred recommendations from our system over random recommendations.