107 citations · 185 across the 24 of their papers we have counts for
25 papers
DashAct: A Progressive Diagnostic Benchmark for GUI Agents in Interactive Dashboard Analysis
Chuhan Zhang, Qi Xie, Ziyue Wang +4
Interactive dashboards require users to reveal and connect evidence across stateful interactions. Although graphical user interface (GUI) agents could automate this process, existi…
DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation
Xiaotong Wang, Dazhen Deng
Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and natural-language goals, but e…
Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework
Yuchen He, Peizhi Ying, Liqi Cheng +4
Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are re…
Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation
Dazhen Deng, Zhaoping He, Xin Qian +3
Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-view interactions, remain out…
ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL
Zhaorui Yang, Huawei Zheng, Sen Yang +14
Large language models have substantially advanced Text-to-SQL systems, yet applying them to enterprise-scale databases remains challenging. Real-world databases often contain large…
EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
Huawei Zheng, Sen Yang, Zhaorui Yang +12
Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and ambiguous databases.…
GraphTide: Augmenting Knowledge-Intensive Text with Progressive Nested Graph
Xin Qian, Dazhen Deng, Zhaoping He +3
Knowledge-intensive text usually contains fruitful entities and complex relationships, such as academic articles and scientific exposition. Reading and comprehending such texts oft…
KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models
Zhenning Chen, Hanbei Zhan, Yanwei Huang +4
Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge ed…
Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues
Tai-Quan Peng, Yuan Tian, Songsong Liang +2
Large language models make agent-based simulation more behaviorally expressive, but they also sharpen a basic methodological tension: fluent, human-like output is not, by itself, e…
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
Huawei Zheng, Xinqi Jiang, Sen Yang +3
Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risks. Domain-specific datasets of h…
CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation
Dazhen Deng, Sen Yang, Yuchen He +2
Current chart-related tasks, such as chart generation (NL2Chart), chart schema parsing, chart data parsing, and chart question answering (ChartQA), are typically studied in isolati…
Linking Heterogeneous Data with Coordinated Agent Flows for Social Media Analysis
Shifu Chen, Dazhen Deng, Zhihong Xu +4
Social media platforms generate volumes of heterogeneous data, capturing user behaviors, textual content, and network structures. Analyzing such data is crucial for understanding p…
ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization
Yuchen He, Jianbing Lv, Liqi Cheng +3
Temporal Action Localization (TAL) aims to detect the start and end timestamps of actions in a video. However, the training of TAL models requires a substantial amount of manually…
ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs
Yuan Tian, Chuhan Zhang, Xiaotong Wang +5
Creating data reports is a labor-intensive task involving iterative data exploration, insight extraction, and narrative construction. A key challenge lies in composing the analysis…
NoteFlow: Leveraging Charts as Sight Glasses for Consistent and Continuous Data Flow Tracing
Yuan Tian, Dazhen Deng, Sen Yang +5
Computational notebooks offer a flexible environment for exploratory data analysis (EDA), but this flexibility often leads to disorganized and iterative execution of notebook cells…
ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis
Yuchen He, Zeqing Yuan, Yihong Wu +3
The immense popularity of racket sports has fueled substantial demand in tactical analysis with broadcast videos. However, existing manual methods require laborious annotation, and…
ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language
Yuan Tian, Weiwei Cui, Dazhen Deng +4
The use of natural language interfaces (NLIs) to create charts is becoming increasingly popular due to the intuitiveness of natural language interactions. One key challenge in this…
VAID: Indexing View Designs in Visual Analytics System
Lu Ying, Aoyu Wu, Haotian Li +7
Visual analytics (VA) systems have been widely used in various application domains. However, VA systems are complex in design, which imposes a serious problem: although the academi…
MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization
Lu Ying, Xinhuan Shu, Dazhen Deng +4
Glyph-based visualization achieves an impressive graphic design when associated with comprehensive visual metaphors, which help audiences effectively grasp the conveyed information…
DashBot: Insight-Driven Dashboard Generation Based on Deep Reinforcement Learning
Dazhen Deng, Aoyu Wu, Huamin Qu +1
Analytical dashboards are popular in business intelligence to facilitate insight discovery with multiple charts. However, creating an effective dashboard is highly demanding, which…
Revisiting the Design Patterns of Composite Visualizations
Dazhen Deng, Weiwei Cui, Xiyu Meng +4
Composite visualization is a popular design strategy that represents complex datasets by integrating multiple visualizations in a meaningful and aesthetic layout, such as juxtaposi…
In Defence of Visual Analytics Systems: Replies to Critics
Aoyu Wu, Dazhen Deng, Furui Cheng +3
The last decade has witnessed many visual analytics (VA) systems that make successful applications to wide-ranging domains like urban analytics and explainable AI. However, their r…
EventAnchor: Reducing Human Interactions in Event Annotation of Racket Sports Videos
Dazhen Deng, Jiang Wu, Jiachen Wang +6
The popularity of racket sports (e.g., tennis and table tennis) leads to high demands for data analysis, such as notational analysis, on player performance. While sports videos off…
PassVizor: Toward Better Understanding of the Dynamics of Soccer Passes
Xiao Xie, Jiachen Wang, Hongye Liang +5
In soccer, passing is the most frequent interaction between players and plays a significant role in creating scoring chances. Experts are interested in analyzing players' passing b…