Erzhen Hu

I am a final-year PhD candidate in Computer Science at the University of Virginia, advised by Prof. Seongkook Heo. Before that, I obtained M.S. in Statistics from University of Virginia, and B.A. in Sociology from Shanghai University.

I develop and study interactive systems that engineer both the scale and nuance of communication, bridging behavioral theories of human interaction with AI-driven authoring and generative tools. These systems span conversational interfaces, avatar-based simulations, and multimodal media. I am a recipient of 2024 Google PhD Fellowship and a MIT EECS Rising Star participant. During the summers, I've interned at Microsoft Research, Google, and Autodesk Research.

Updates

Jun 2026: ReliveMeet (w/ Microsoft Research) accepted at Graphics Interface 2026.
Apr 2026: Presented PrevizWhiz, a genAI–powered previsualization system for filmmaking, at CHI 2026.
Feb 2026: Check out our latest coverage of DialogLab at Google Research Blog and X post, highlighting a new framework for authoring and simulating dynamic human-AI group conversations.
Jan 2026: Gave a talk at ICXR research series.
Jan 2026: Two CHI 2026 papers accepted: 1st-authored PrevizWhiz (w/ Autodesk Research) and co-authored Redirected Pinch.
Oct 2025: I will be attending the EECS Rising Stars 2025 workshop hosted by MIT and BU.
Sep 2025: Passed thesis proposal!
Aug 2025: Two first-author papers, DialogLab, and Thing2Reality has been accepted by UIST 2025.
Feb 2025: One first-author paper accepted by CSCW 2025.
Oct 2024: Demoed Thing2Reality at UIST 2024.
Jun 2024: I have passed the Qualifying Exam and have become a Ph.D. candidate!
Mar 2023: Presented OpenMic and ThingShare on Apr 25th (Tue). Check out the CHI 2023 program!
Jan 2023: Two first-author papers accepted at CHI 2023.
Nov 2022: Serving as CHI 2023 Late-Breaking Work (LBW) Program Committee member.
Oct 2022: Reviewed CHI 2023 papers (1*special recognition) and SVed at UIST 2022.
May 2022: Presented FluidMeet paper at CHI 2022 in New Orleans.
Mar 2022: Presented FluidMeet at the Virtual Social Presence Seminar. You can watch the recorded 40-min talk here.

Recent Publications

PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualization

Erzhen Hu, Frederik Brudy, David Ledo, George Fitzmaurice, Fraser Anderson

CHI 2026

PrevizWhiz helps filmmakers quickly prototype cinematic shots by combining rough 3D blocking with AI-generated, stylized video previews, and customizing adherence levels between 3D and 2D.

🔗 DOI 🔗 Arxiv 📄 PDF 🎬 Video

DialogLab: Authoring, Simulating, and Testing Dynamic Human-AI Group Conversations Code Available

Erzhen Hu, Yanhe Chen, Mingyi Li, Vrushank Phadnis, Pingmei Xu, Xun Qian, Alex Olwal, David Kim, Seongkook Heo, Ruofei Du

UIST 2025

DialogLab provides a unified interface to configure conversational scenes, define agent personas, manage group structures, specify turn-taking rules, and orchestrate transitions between scripted narratives and improvisation.

🔗 DOI 📄 PDF 🎬 Video 30s Preview Talk 🌐 Demo GitHub

Thing2Reality: Enabling Spontaneous Creation of 3D Objects from 2D Content using Generative AI in XR Meetings

Erzhen Hu, Mingyi Li, Jungtaek Hong, Xun Qian, Alex Olwal, David Kim, Seongkook Heo, Ruofei Du

UIST 2025

Leverage multi-view diffusion models and 3D Gaussian Splatting to enhance XR communication and collaboration around objects.

🔗 DOI 📄 PDF 30s Preview 🎬 Video Talk Project

All publications

Service

Program Committee Member: C&C 2025 Papers,CHI 2023-2024 LBW, CSCW 2024 Demo and Poster

Reviewer for CHI 2023(*)-2025(*4), CSCW 2022 & 2024 (*), UIST 2023-2025(*), C&C 2024 (*), MobileHCI 2022(*), Auto UI 2022, NordiCHI 2022(*)

(*) Special Recognitions for Outstanding Reviews

Student Volunteer for ACM CSCW 2022, ACM UIST 2022, ACM IUI 2022, IEEE VR 2022, ACM ISS 2021

Design and source code from Link