Publications
VAChat: Understanding and Alleviating Asymmetry in Communication for Visual Analytics Collaboration
CSCW 2026OngoingWeichen Sun, Junxiu Tang, Linping Yuan, Feiyuan Qu, Junming Gao, Ut Gong, Xiaojiao Chen, Tan Tang
This paper addresses communication asymmetries in visual analytics collaborations—differences in cognitive understanding and resource access that are often overlooked in traditional frameworks. It introduces VisAuto-Communication (VAC), an AI-assisted system that structures replies and improves mutual understanding, demonstrating significant gains in efficiency and engagement. The study contributes design implications for collaboration-aware computing systems.
VAChat: Understanding and Alleviating Asymmetry in Communication for Visual Analytics Collaboration
CSCW 2026OngoingWeichen Sun, Junxiu Tang, Linping Yuan, Feiyuan Qu, Junming Gao, Ut Gong, Xiaojiao Chen, Tan Tang
This paper addresses communication asymmetries in visual analytics collaborations—differences in cognitive understanding and resource access that are often overlooked in traditional frameworks. It introduces VisAuto-Communication (VAC), an AI-assisted system that structures replies and improves mutual understanding, demonstrating significant gains in efficiency and engagement. The study contributes design implications for collaboration-aware computing systems.
My Role: Conception, Paper Writing
From Silence to Care: Exploring AI-Mediated Approaches for Healthcare Communication
CSCW 2026OngoingUt Gong, Yibo Meng, Ye Wang
This work explores AI-mediated communication approaches in healthcare to bridge asymmetry between doctors and patients. Through formative studies and prototype evaluation, it identifies how LLMs can support empathic, clear, and balanced exchanges in clinical settings, improving both comprehension and efficiency in consultations.
From Silence to Care: Exploring AI-Mediated Approaches for Healthcare Communication
CSCW 2026OngoingUt Gong, Yibo Meng, Ye Wang
This work explores AI-mediated communication approaches in healthcare to bridge asymmetry between doctors and patients. Through formative studies and prototype evaluation, it identifies how LLMs can support empathic, clear, and balanced exchanges in clinical settings, improving both comprehension and efficiency in consultations.
My Role: Conception, Formative Study, Paper Writing
TactiCast: Context-Aware Viewpoint Blending for Immersive Tactical Analysis
IEEE VIS 2026OngoingUt Gong, Jiaqi Hou, Qihan Zhang, Stefanie Zollmann
TactiCast introduces a context-aware blending mechanism that combines multiple tactical viewpoints in immersive soccer analysis. The system integrates automatic perspective selection and player-role context to improve tactic comprehension and communication for coaches and players in XR environments.
TactiCast: Context-Aware Viewpoint Blending for Immersive Tactical Analysis
IEEE VIS 2026OngoingUt Gong, Jiaqi Hou, Qihan Zhang, Stefanie Zollmann
TactiCast introduces a context-aware blending mechanism that combines multiple tactical viewpoints in immersive soccer analysis. The system integrates automatic perspective selection and player-role context to improve tactic comprehension and communication for coaches and players in XR environments.
My Role: Conception, Formative Study, Implementation, Paper Writing
CLEAR: A Bidirectional Framework for Enhancing Doctor-Patient Communication in Resource-Constrained Healthcare Settings
CHI 2026Under ReviewUt Gong, Rong Fu, Yibo Meng, Zeyu Chen, Yan Guan
CLEAR (Contextual Learning and Explanation Agent for Results) improves medical communication in low-resource settings. Built on domain-specialized LLMs and ReAct methodology, it reduces consultation time and enhances patient comprehension through six key components: profile management, explanation generation, and multimodal outputs. Evaluations showed 98% explanation accuracy and strong user satisfaction.
CLEAR: A Bidirectional Framework for Enhancing Doctor-Patient Communication in Resource-Constrained Healthcare Settings
CHI 2026Under ReviewUt Gong, Rong Fu, Yibo Meng, Zeyu Chen, Yan Guan
CLEAR (Contextual Learning and Explanation Agent for Results) improves medical communication in low-resource settings. Built on domain-specialized LLMs and ReAct methodology, it reduces consultation time and enhances patient comprehension through six key components: profile management, explanation generation, and multimodal outputs. Evaluations showed 98% explanation accuracy and strong user satisfaction.
My Role: Conception, Formative Study, Implementation, Evaluation, Paper Writing
LGV-MKC: Large-Scale Graph Visualization through Mutual K-Core Identification
CHI 2026Under ReviewYuting Chen, Ut Gong, Yiyang Yang, Can Chen
NV-MKCore introduces a scalable visualization framework for large networks based on mutual K-core decomposition, enabling clearer structural exploration and efficient visual summarization of dense graphs. The system integrates node aggregation, core membership encoding, and dynamic filtering for network insight discovery.
LGV-MKC: Large-Scale Graph Visualization through Mutual K-Core Identification
CHI 2026Under ReviewYuting Chen, Ut Gong, Yiyang Yang, Can Chen
NV-MKCore introduces a scalable visualization framework for large networks based on mutual K-core decomposition, enabling clearer structural exploration and efficient visual summarization of dense graphs. The system integrates node aggregation, core membership encoding, and dynamic filtering for network insight discovery.
My Role: Conception, Visualization Design, Paper Writing
CABoard: Creating AI-driven Dynamic Collage Arts to Enhance Visual Communication
CHI 2026Under ReviewWeichen Sun, Tan Tang, Yuxiao Yang, Lu Ying, Ut Gong, Junxiu Tang, Yingcai Wu
CABoard is an AI-driven dynamic collage system for creative ideation and narrative communication. Using multi-agent LLM coordination and a Designer-in-the-Loop paradigm, CABoard enables progressive 2.5D storytelling through adaptive image synthesis, layout control, and semantic guidance.
CABoard: Creating AI-driven Dynamic Collage Arts to Enhance Visual Communication
CHI 2026Under ReviewWeichen Sun, Tan Tang, Yuxiao Yang, Lu Ying, Ut Gong, Junxiu Tang, Yingcai Wu
CABoard is an AI-driven dynamic collage system for creative ideation and narrative communication. Using multi-agent LLM coordination and a Designer-in-the-Loop paradigm, CABoard enables progressive 2.5D storytelling through adaptive image synthesis, layout control, and semantic guidance.
My Role: Conception, System Design, Agent Implementation, Paper Writing
TimeFolder: A Universal Framework for Enhancing Visualization Across Time-Oriented Data Methods
Information Visualization (Under Review)Under ReviewUt Gong, Weichen Sun, Shuhan Liu, Yang Liu, Tan Tang, Yingcai Wu
TimeFolder applies the Minimum Description Length principle to compress long-term temporal data while preserving analytical fidelity. By balancing information density and visual saliency, it provides a universal interface for multi-scale time-series visualization.
TimeFolder: A Universal Framework for Enhancing Visualization Across Time-Oriented Data Methods
Information Visualization (Under Review)Under ReviewUt Gong, Weichen Sun, Shuhan Liu, Yang Liu, Tan Tang, Yingcai Wu
TimeFolder applies the Minimum Description Length principle to compress long-term temporal data while preserving analytical fidelity. By balancing information density and visual saliency, it provides a universal interface for multi-scale time-series visualization.
My Role: Conception, Implementation, Evaluation, Paper Writing
VAIR: Visual Analytics for Injury Risk Exploration in Sports
16th Workshop on Visual Analytics in Healthcare (VAHC) at IEEE VIS 2025AcceptedChunggi Lee, Ut Gong, Tica Lin, Hanspeter Pfister
VAIR integrates SMPL-based motion reconstruction with OpenSim-based risk modeling to visualize biomechanical loads across movement phases. The system maps injury risks using a structured Haddon Matrix and supports interactive exploration through 3D visualization and synchronized temporal plots.
VAIR: Visual Analytics for Injury Risk Exploration in Sports
16th Workshop on Visual Analytics in Healthcare (VAHC) at IEEE VIS 2025AcceptedChunggi Lee, Ut Gong, Tica Lin, Hanspeter Pfister
VAIR integrates SMPL-based motion reconstruction with OpenSim-based risk modeling to visualize biomechanical loads across movement phases. The system maps injury risks using a structured Haddon Matrix and supports interactive exploration through 3D visualization and synchronized temporal plots.
My Role: Conception, Implementation, Evaluation, Paper Writing
Augmented Reality for Supporting Accessible Sports Spectating and Training
Metaverse CHI 2025 WorkshopAcceptedStefanie Zollmann, Ut Gong, Tobias Langlot
This work explores how AR can enhance accessibility in sports spectating and training by providing adaptive visual and contextual information to audiences and athletes with varied sensory needs. It offers a design space for inclusive AR-assisted experiences.
Augmented Reality for Supporting Accessible Sports Spectating and Training
Metaverse CHI 2025 WorkshopAcceptedStefanie Zollmann, Ut Gong, Tobias Langlot
This work explores how AR can enhance accessibility in sports spectating and training by providing adaptive visual and contextual information to audiences and athletes with varied sensory needs. It offers a design space for inclusive AR-assisted experiences.
My Role: Conception, Paper Writing
Collaborative XRTactics: A Formative Study on Tactical Communication in Outdoor Team Sports
IEEE VIS 2024 WorkshopAcceptedUt Gong, Qihan Zhang, Ziqing Yin, Stefanie Zollmann
This formative study investigates communication challenges in outdoor team sports and proposes XR-based tactical visualization to improve coordination and understanding among players and coaches. Insights inform the design of immersive sports analytics systems.
Collaborative XRTactics: A Formative Study on Tactical Communication in Outdoor Team Sports
IEEE VIS 2024 WorkshopAcceptedUt Gong, Qihan Zhang, Ziqing Yin, Stefanie Zollmann
This formative study investigates communication challenges in outdoor team sports and proposes XR-based tactical visualization to improve coordination and understanding among players and coaches. Insights inform the design of immersive sports analytics systems.
My Role: Conception, Formative Study, Implementation, Paper Writing
VolleyNaut: Pioneering Immersive Training for Inclusive Sitting Volleyball Skill Development
IEEE VR 2024AcceptedUt Gong, Hanze Jia, Yujie Wang, Tan Tang, Xiao Xie, Yingcai Wu
VolleyNaut enables accessible sitting volleyball training through immersive VR drills and adaptive ball pitching. Designed with input from national coaches, it improves skill learning and engagement, especially for athletes with disabilities.
VolleyNaut: Pioneering Immersive Training for Inclusive Sitting Volleyball Skill Development
IEEE VR 2024AcceptedUt Gong, Hanze Jia, Yujie Wang, Tan Tang, Xiao Xie, Yingcai Wu
VolleyNaut enables accessible sitting volleyball training through immersive VR drills and adaptive ball pitching. Designed with input from national coaches, it improves skill learning and engagement, especially for athletes with disabilities.
My Role: Conception, Formative Study, Implementation, Evaluation, Paper Writing