Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents
本文提出Lexara-RF，一种无需参考基准的评估方法，通过计算一致性、意图对齐和设计有效性来评估对话式视觉分析代理的多模态输出。
0 citationsRead paper
Selected work
Representative Papers
Ptolemy: A Semantic Map of Exploratory Data Analysis
该研究通过构建一个名为Ptolemy的语义地图来解决探索性数据分析过程中难以追踪已分析内容的问题，利用结构化描述生成嵌入式位置表示每个分析步骤，以提高全局定位和局部比较能力。
0 citationsRead paper
AI Agents and the Future of VIS
This project addresses the interaction adaptability challenges arising from autonomous AI agents reshaping visualization paradigms by systematically investigating the deep integration of agents and visualization. Through a hybrid format combining keynotes, paper discussions, and the inaugural Agentic VIS Challenge, it establishes a human-agent collaborative framework and a practical validation platform. By convening domain researchers to explore agent integration strategies, this initiative not only delineates new research directions for visualization in the agentic era but also provides theoretical foundations and innovative benchmarks for next-generation human-AI collaborative visualization. Ultimately, this work facilitates the field’s adaptation to intelligent transformations, offering critical insights into the coexistence and synergy between autonomous agents and visual analytics systems.
0 citationsRead paper
Not Always Top-Left: Untangling the Signals that Guide Dashboard Reading Order
This study addresses the mismatch between assumed and actual user reading behaviors in dashboard design, where existing approaches often presume a fixed component viewing order. Through a mixed-methods investigation involving 18 designers and 16 users, the work systematically identifies and quantifies six key factors influencing interaction sequences: layout, visual salience, semantics, functional role, interactivity, and user context. Integrating interviews, behavioral logs, and sequential analysis, the research uncovers both consistent patterns and diverse strategies in how users navigate dashboards, revealing representative navigation pathways. These findings provide an empirical foundation and actionable design insights for computational modeling of dashboard comprehension and the development of intelligent guidance systems that adapt to real user behavior.
0 citationsRead paper
From 'Here' to 'There': Exploring Proximity Semantics in Multimodal Data Exploration
This study addresses the challenge that existing data exploration tools struggle to accurately interpret users’ analytical intent when expressed in unstructured forms within spatiotemporal datasets. To bridge this gap, the authors propose a multimodal query system integrating freehand sketching, natural language, and visual annotations. Central to their approach is the concept of “proxemic semantics,” which captures how users disambiguate references through the relative spatial arrangement of multimodal elements within a unified interaction space. The system employs a hybrid architecture combining geometric sketch matching with vision-language models (VLMs), enabling joint pattern matching and semantic constraint-based query parsing. A user study with 20 participants empirically validates the stability of proxemic semantics, offering both empirical grounding and design implications for multimodal data exploration interfaces.
0 citationsRead paper
Recent publications
Latest Papers
Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents
本文提出Lexara-RF，一种无需参考基准的评估方法，通过计算一致性、意图对齐和设计有效性来评估对话式视觉分析代理的多模态输出。
0 citationsRead paper
Ptolemy: A Semantic Map of Exploratory Data Analysis
该研究通过构建一个名为Ptolemy的语义地图来解决探索性数据分析过程中难以追踪已分析内容的问题，利用结构化描述生成嵌入式位置表示每个分析步骤，以提高全局定位和局部比较能力。
0 citationsRead paper
AI Agents and the Future of VIS
This project addresses the interaction adaptability challenges arising from autonomous AI agents reshaping visualization paradigms by systematically investigating the deep integration of agents and visualization. Through a hybrid format combining keynotes, paper discussions, and the inaugural Agentic VIS Challenge, it establishes a human-agent collaborative framework and a practical validation platform. By convening domain researchers to explore agent integration strategies, this initiative not only delineates new research directions for visualization in the agentic era but also provides theoretical foundations and innovative benchmarks for next-generation human-AI collaborative visualization. Ultimately, this work facilitates the field’s adaptation to intelligent transformations, offering critical insights into the coexistence and synergy between autonomous agents and visual analytics systems.
0 citationsRead paper
Not Always Top-Left: Untangling the Signals that Guide Dashboard Reading Order
This study addresses the mismatch between assumed and actual user reading behaviors in dashboard design, where existing approaches often presume a fixed component viewing order. Through a mixed-methods investigation involving 18 designers and 16 users, the work systematically identifies and quantifies six key factors influencing interaction sequences: layout, visual salience, semantics, functional role, interactivity, and user context. Integrating interviews, behavioral logs, and sequential analysis, the research uncovers both consistent patterns and diverse strategies in how users navigate dashboards, revealing representative navigation pathways. These findings provide an empirical foundation and actionable design insights for computational modeling of dashboard comprehension and the development of intelligent guidance systems that adapt to real user behavior.
0 citationsRead paper
From 'Here' to 'There': Exploring Proximity Semantics in Multimodal Data Exploration
This study addresses the challenge that existing data exploration tools struggle to accurately interpret users’ analytical intent when expressed in unstructured forms within spatiotemporal datasets. To bridge this gap, the authors propose a multimodal query system integrating freehand sketching, natural language, and visual annotations. Central to their approach is the concept of “proxemic semantics,” which captures how users disambiguate references through the relative spatial arrangement of multimodal elements within a unified interaction space. The system employs a hybrid architecture combining geometric sketch matching with vision-language models (VLMs), enabling joint pattern matching and semantic constraint-based query parsing. A user study with 20 participants empirically validates the stability of proxemic semantics, offering both empirical grounding and design implications for multimodal data exploration interfaces.
0 citationsRead paper