Tovi Grossman

Script2Screen: Supporting Dialogue-Centric Scriptwriting with Interactive Audiovisual Generation

Zhecheng Wang, Jiaju Ma, Eitan Grinspun, Tovi Grossman et autres

Scriptwriting has traditionally been text-centric, a modality that only partially conveys the produced audiovisual experience. A formative study with professional writers informed us that connecting textual and audiovisual modalities can aid ideation and iteration, especially for writing dialogues. In this work, we …

ca, us (code pays fourni par la source)

Gazeify Then Voiceify: Physical Object Referencing Through Gaze and Voice Interaction with Displayless Smart Glasses

Zheng Zhang, Mengjie Yu, Tianyi Wang, Kashyap Todi et autres

Smart glasses enhance interactions with the environment by using head-mounted cameras to observe the user’s viewpoint, but lack the visual feedback used for common interactions. We introduce “Gazeify then Voiceify”, a multimodal approach allowing object selection via gaze and voice using displayless …

us, ca (code pays fourni par la source)

Script2Screen: Supporting Dialogue-Centric Scriptwriting with Interactive Audiovisual Generation

Zhecheng Wang, J Ma, Eitan Grinspun, Tovi Grossman et autres

Scriptwriting has traditionally been text-centric, a modality that only partially conveys the produced audiovisual experience. A formative study with professional writers informed us that connecting textual and audiovisual modalities can aid ideation and iteration, especially for writing dialogues. In this work, we …

ca, us (code pays fourni par la source)

Gazeify Then Voiceify: Physical Object Referencing Through Gaze and Voice Interaction with Displayless Smart Glasses

Zheng Zhang, Mengjie Yu, Tianyi Wang, Kashyap Todi et autres

Smart glasses enhance interactions with the environment by using head-mounted cameras to observe the user's viewpoint, but lack the visual feedback used for common interactions. We introduce Gazeify then Voiceify, a multimodal approach allowing object selection via gaze and voice using displayless …

LOOM: Personalized Learning Informed by Daily LLM Conversations Toward Long-Term Mastery via a Dynamic Learner Memory Graph

Kevin Pu, Tovi Grossman

Foundation models are increasingly used to personalize learning, yet many systems still assume fixed curricula or coarse progress signals, limiting alignment with learners' day-to-day needs. At the other extreme, lightweight incidental systems offer flexible, in-the-moment content but rarely guide learners toward mastery. …

STAR: Smartphone-analogous Typing in Augmented Reality

Taejun Kim, Amy Karlson, Aakar Gupta, Tovi Grossman et autres

While text entry is an essential and frequent task in Augmented Reality (AR) applications, devising an efficient and easy-to-use text entry method for AR remains an open challenge. This research presents STAR, a smartphone-analogous AR text entry technique that leverages a user's …

KnowledgeTrail: Generative Timeline for Exploration and Sensemaking of Historical Events and Knowledge Formation

Sangho Suh, Rahul Hingorani, Bryan Wang, Tovi Grossman

The landscape of interactive systems is shifting toward dynamic, generative experiences that empower users to explore and construct knowledge in real time. Yet, timelines -- a fundamental tool for representing historical and conceptual development -- remain largely static, limiting user agency and …

Investigating Aggregated vs. Sequential Command Recommendation in Graphical User Interfaces

Ben Lafreniere, Zachary J Davis, Michelle Li, Junmeng Andrew Han et autres

Advances in artificial intelligence open the possibility of predicting and recommending sequences of GUI commands to a user. An interesting question raised by this capability is how to present such recommendations to the user – as a sequential set of individual command …

us, ca (code pays fourni par la source)

Investigating Augmented Reality for Adaptive Motor-Skill Training

Dishita G Turakhia, Mark Parent, Tovi Grossman, Michael Glueck et autres

Adaptive training of motor-skills, where the difficulty level of the training task is adapted optimally based on the learner’s skill levels, has been shown to enable higher learning gains compared to non-adaptive training. However, prior approaches rely on adapting physical tools that …

us, ca (code pays fourni par la source)

A Multimodal Approach for Targeting Error Detection in Virtual Reality Using Implicit User Behavior

Naveen Sendhilnathan, Ting Zhang, David Bethge, Michael Nebeling et autres

Although the point-and-select interaction method has been shown to lead to user and system-initiated errors, it is still prevalent in VR scenarios.Current solutions to facilitate selection interactions exist, however they do not address the challenges caused by targeting inaccuracy.To reduce the effort …

us, ca (code pays fourni par la source)

MaRginalia: Enabling In-person Lecture Capturing and Note-taking Through Mixed Reality

Leping Qiu, E. S. Kim, Sangho Suh, Ludwig Sidenmark et autres

Students often take digital notes during live lectures, but current methods can be slow when capturing information from lecture slides or the instructor's speech, and require them to focus on their devices, leading to distractions and missing important details. This paper explores …

ca (code pays fourni par la source)

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

Kevin Pu, K. J. Kevin Feng, Tovi Grossman, Tom Hope et autres

ca, us (code pays fourni par la source)