About

I am an Assistant Professor (Research) at the Graduate School of Education and Computer Science (by courtesy) at Stanford University. I am also the Ram and Vijay Shriram Faculty Fellow at the Institute for Human-Centered AI (HAI) and a core faculty member of Stanford HCI. My research asks how we design AI to extend human thinking rather than replace it. I take a cognitively grounded approach to HCI, studying how people build knowledge through acts of creation: writing arguments, building models, drawing diagrams. I then design interfaces that make these cognitive structures visible and interactive, so that AI can meaningfully participate in the process without taking it over. This work spans AI thinking tools that preserve learners' roles as active creators, pedagogical systems that help teachers see and support how students learn, and design methods that give educators real agency in shaping the AI tools entering their classrooms.

Research topics

• Computer Science
• Sociology
• Business
• Knowledge management
• Engineering
• Process management

Selected publications

• Deep Sketch-Based 3D Modeling: A Survey

  arXiv (Cornell University) · 2026-01-22

  preprintOpen access

  In the past decade, advances in artificial intelligence have revolutionized sketch-based 3D modeling, leading to a new paradigm known as Deep Sketch-Based 3D Modeling (DS-3DM). DS-3DM offers data-driven methods that address the long-standing challenges of sketch abstraction and ambiguity. DS-3DM keeps humans at the center of the creative process by enhancing the flexibility, usability, faithfulness, and adaptability of sketch-based 3D modeling interfaces. This paper contributes a comprehensive survey of the latest DS-3DM within a novel design space: MORPHEUS. Built upon the Input-Model-Output (IMO) framework, MORPHEUS categorizes Models outputting Options of 3D Representations and Parts, derived from Human inputs (varying in quantity and modality), and Evaluated across diverse User-views and Styles. Throughout MORPHEUS we highlight limitations and identify opportunities for interdisciplinary research in Computer Vision, Computer Graphics, and Human-Computer Interaction, revealing a need for controllability and information-rich outputs. These opportunities align design processes more closely with user' intent, responding to the growing importance of user-centered approaches.

  PublisherDOI

• Deep Sketch‐Based 3D Modeling: A Survey

  Computer Graphics Forum · 2026-02-12

  article

  Abstract In the past decade, advances in artificial intelligence have revolutionised sketch‐based 3D modelling, leading to a new paradigm known as Deep Sketch‐Based 3D Modelling (). offers data‐driven methods that address the long‐standing challenges of sketch abstraction and ambiguity. keeps humans at the centre of the creative process by enhancing the flexibility, usability, faithfulness, and adaptability of sketch‐based 3D modelling interfaces. This paper contributes a comprehensive survey of the latest DS‐3DM within a novel design space: MORPHEUS . Built upon the Input‐Model‐Output (IMO) framework, MORPHEUS categorises M odels outputting O ptions of 3D R epresentations and P arts, derived from H uman‐inputs (varying in quantity and modality), and E valuated across diverse U ser‐views and S tyles. Throughout , we highlight limitations and identify opportunities for interdisciplinary research in computer vision, computer graphics, and human–computer interaction, revealing a need for controllability and information‐rich outputs. These opportunities align design processes more closely with user' intent, responding to the growing importance of user‐centred approaches.

  PublisherDOI

• Generative Design and Vibe Coding: Rethinking The Design-Development Divide for UI Prototyping

  2026-04-13

  articleOpen access

  Prototyping has long been central to HCI as a way of knowing for exploring and communicating design ideas. Recent advances in Generative AI Practices—from Generative Design to Vibe Coding—are reshaping who prototypes and how. These approaches blur boundaries between designers and developers, enabling faster, more inclusive workflows while raising new challenges around trust, authorship, and control. This CHI 2026 meet-up will gather researchers and practitioners to discuss how AI-assisted prototyping transforms Houde and Hill’s dimensions of look and feel and implementation. Through a hands-on Designathon, participants will reflect on opportunities, breakdowns, and best practices for human–AI collaboration in prototyping.

  PublisherDOI

• Metacognitive Demands and Strategies While Using Off-The-Shelf AI Conversational Agents for Health Information

  Open MIND · 2026-02-04

  preprint

  As Artificial Intelligence (AI) conversational agents become widespread, people are increasingly using them for health information seeking. The use of off-the-shelf conversational agents for health information seeking could place high metacognitive demands (the need for extensive monitoring and control of one's own thought process) on individuals, which could compromise their experience of seeking health information. However, currently, the specific demands that arise while using conversational agents for health information seeking, and the strategies people use to cope with those demands, remain unknown. To address these gaps, we conducted a think-aloud study with 15 participants as they sought health information using our off-the-shelf AI conversational agent. We identified the metacognitive demands such systems impose, the strategies people adopt in response, and propose considerations for designing beyond off-the-shelf interfaces to reduce these demands and support better user experiences and affordances in health information seeking.

  DOI

• Deep Sketch-Based 3D Modeling: A Survey

  arXiv (Cornell University) · 2026-01-22

  articleOpen access

  In the past decade, advances in artificial intelligence have revolutionized sketch-based 3D modeling, leading to a new paradigm known as Deep Sketch-Based 3D Modeling (DS-3DM). DS-3DM offers data-driven methods that address the long-standing challenges of sketch abstraction and ambiguity. DS-3DM keeps humans at the center of the creative process by enhancing the flexibility, usability, faithfulness, and adaptability of sketch-based 3D modeling interfaces. This paper contributes a comprehensive survey of the latest DS-3DM within a novel design space: MORPHEUS. Built upon the Input-Model-Output (IMO) framework, MORPHEUS categorizes Models outputting Options of 3D Representations and Parts, derived from Human inputs (varying in quantity and modality), and Evaluated across diverse User-views and Styles. Throughout MORPHEUS we highlight limitations and identify opportunities for interdisciplinary research in Computer Vision, Computer Graphics, and Human-Computer Interaction, revealing a need for controllability and information-rich outputs. These opportunities align design processes more closely with user' intent, responding to the growing importance of user-centered approaches.

  PublisherOA PDF

• Metacognitive Demands and Strategies While Using Off-The-Shelf AI Conversational Agents for Health Information Seeking

  2026-04-13 · 1 citations

  articleOpen access

  As Artificial Intelligence (AI) conversational agents become widespread, people are increasingly using them for health information seeking. The use of off-the-shelf conversational agents for health information seeking could place high metacognitive demands (the need for extensive monitoring and control of one’s own thought process) on individuals, which could compromise their experience of seeking health information. However, currently, the specific demands that arise while using conversational agents for health information seeking, and the strategies people use to cope with those demands, remain unknown. To address these gaps, we conducted a think-aloud study with 15 participants as they sought health information using our off-the-shelf AI conversational agent. We identified the metacognitive demands such systems impose, the strategies people adopt in response, and propose considerations for designing beyond off-the-shelf interfaces to reduce these demands and support better user experiences and affordances in health information seeking.

  PublisherDOI

• Narrative Scaffolding: A Narrative-First Framework for Data-Driven Sensemaking

  2026-03-03 · 1 citations

  articleOpen access

  When exploring data, analysts construct narratives about what the data means by asking questions, generating visualizations, reflecting on patterns, and revising their interpretations as new insights emerge. Yet existing analysis tools treat narrative as an afterthought, breaking the link between reasoning, reflection, and the evolving story from exploration. Consequently, analysts lose the ability to see how their reasoning evolves, making it harder to reflect systematically or build coherent explanations. To address this gap, we propose Narrative Scaffolding (NS), a framework for narrative-driven exploration that positions narrative construction as the primary interface for exploration and reasoning. We implemented this framework in a system that externalizes iterative reasoning through narrative-first entry, semantically aligned view generation, and reflection support via insight provenance and inquiry tracking. In a within-subject study (N = 20), we demonstrated that narrative scaffolding facilitates broader exploration, deeper reflection, and more defensible narratives. An evaluation with visualization literacy experts (N = 6) confirmed that the system produced outputs aligned with narrative intent and facilitated intentional exploration.

  PublisherDOI

• ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent

  ArXiv.org · 2026-02-05

  articleOpen accessSenior author

  Generative AI often produces results misaligned with user intentions, for example, resolving ambiguous prompts in unexpected ways. Despite existing approaches to clarify intent, a major challenge remains: understanding and influencing AI's interpretation of user intent through simple, direct inputs requiring no expertise or rigid procedures. We present ToMigo, representing intent as design concept graphs: nodes represent choices of purpose, content, or style, while edges link them with interpretable explanations. Applied to graphic design, ToMigo infers intent from reference images and text. We derived a schema of node types and edges from pre-study data, informing a multimodal large language model to generate graphs aligning nodes externally with user intent and internally toward a unified design goal. This structure enables users to explore AI reasoning and directly manipulate the design concept. In our user studies, ToMigo received high alignment ratings and captured most user intentions well. Users reported greater control and found interactive features-editable graphs, reflective chats, concept-design realignment-useful for evolving and realizing their design ideas.

  PublisherOA PDF

• ToMigo: Interpretable Design Concept Graphs for Aligning Generative AI with Creative Intent

  Open MIND · 2026-02-05

  preprintSenior author

  Generative AI often produces results misaligned with user intentions, for example, resolving ambiguous prompts in unexpected ways. Despite existing approaches to clarify intent, a major challenge remains: understanding and influencing AI's interpretation of user intent through simple, direct inputs requiring no expertise or rigid procedures. We present ToMigo, representing intent as design concept graphs: nodes represent choices of purpose, content, or style, while edges link them with interpretable explanations. Applied to graphic design, ToMigo infers intent from reference images and text. We derived a schema of node types and edges from pre-study data, informing a multimodal large language model to generate graphs aligning nodes externally with user intent and internally toward a unified design goal. This structure enables users to explore AI reasoning and directly manipulate the design concept. In our user studies, ToMigo received high alignment ratings and captured most user intentions well. Users reported greater control and found interactive features-editable graphs, reflective chats, concept-design realignment-useful for evolving and realizing their design ideas.

  DOI

• Narrative Scaffolding: A Narrative-First Framework for Data-Driven Sensemaking

  arXiv (Cornell University) · 2025-12-21

  preprintOpen access

  When exploring data, analysts construct narratives about what the data means by asking questions, generating visualizations, reflecting on patterns, and revising their interpretations as new insights emerge. Yet existing analysis tools treat narrative as an afterthought, breaking the link between reasoning, reflection, and the evolving story from exploration. Consequently, analysts lose the ability to see how their reasoning evolves, making it harder to reflect systematically or build coherent explanations. To address this gap, we propose Narrative Scaffolding, a framework for narrative-driven exploration that positions narrative construction as the primary interface for exploration and reasoning. We implement this framework in a system that externalizes iterative reasoning through narrative-first entry, semantically aligned view generation, and reflection support via insight provenance and inquiry tracking. In a within-subject study N=20, we demonstrate that narrative scaffolding facilitates broader exploration, deeper reflection, and more defensible narratives. An evaluation with visualization literacy experts (N = 6) confirmed that the system produced outputs aligned with narrative intent and facilitated intentional exploration.

  PublisherDOI

Frequent coauthors

• Eytan Adar

  University of Michigan–Ann Arbor

  29 shared

• Colleen M. Seifert

  Purdue University System

  25 shared

• Stephanie Zellers

  University of Helsinki

  6 shared

• J.W. Jones Son.

  6 shared

• Juho Kim

  Korea Advanced Institute of Science and Technology

  5 shared

• Jennifer Wortman Vaughan

  5 shared

• Shakhnozakhon Yadgarova

  4 shared

• Hyungyu Shin

  Korea Advanced Institute of Science and Technology

  4 shared

Labs

• Hariharan Subramonyam LabPI

Education

• Ph.D., Information

  University of Michigan School of Information

• M.S., Information

  University of Michigan School of Information

Awards & honors

• Best paper awards at top human-computer interaction conferen…