Data Visualization and Analytics

Latest papers

• Where LLMs Fail with Visualization DSLs

  Chang Han, Andrew McNutt, Katherine Isaacs · 2 October 2026

  As LLMs take up the role of authoring charts using visualization domain-specific languages (DSLs), the human constraints that shaped those languages may no longer apply, as what is easy for a person is not necessarily easy for a model. To understand how LLMs might work better with DSLs, we explore w…

• Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation

  Yuxin Yue, Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Xueqi Cheng · 2 October 2026

  Analytical charts in multimodal deep research encode quantitative claims, requiring every visualized value to be faithfully grounded in supporting evidence. Unlike retrieved images that mainly provide contextual information, charts require numerical fidelity: visualized values should not only match …

• InfoAgent: Traceable Generation and Repair of Evidence-Grounded Infographics

  Yifan Li, Tong Li, Qi Zeng, Lishuai Gao, Ruwei Pan, Cong Wei, Shaohua Kevin Zhou, Zhuoliang Kang, Xiaoming Wei · 1 October 2026

  Reliable infographic generation requires facts, symbols, and visual relations to remain consistent through rendering and revision. Correcting one element also requires tracking its supporting evidence and the dependencies affected by the change. We present \textbf{InfoAgent}, a training-free framewo…

• When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning

  Yunbei Zhang, Janet Wang, Jihun Hamm, Chandan K Reddy · 1 October 2026

  Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to use information that is present. We introduce a diagnostic protocol to distinguish these explanation…

• ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density

  Xinhe Wu, Yadong Jin · 1 October 2026

  Multimodal large language models (MLLMs) offer a promising approach for recovering numerical data from scientific charts, but their ability to reconstruct chart data from visually dense figures remains poorly understood. Existing chart understanding benchmarks primarily evaluate question answering o…

• ChartRevise: A Dataset and Evaluation Protocol for Exact Chart Editing via Code

  Jiaxiang Tang, Yi Zhou, Chad DeLuca, Rogerio Feris, Ahmed Khalil Omran, Zhi-Li Zhang, Pengyuan Li, Ali Anwar · 1 October 2026

  Chart editing requires cross-modal edit grounding, realizing a requested visual change in the code that draws it, with necessary related updates and without altering unrelated content. Existing benchmarks emphasize either code executability or chart quality, but their metrics do not clearly distingu…

• InfoEdit: Probing Global Layout Reasoning in Infographic Editing

  Cheng Yang, Chufan Shi, Huijuan Wang, Bo Shui, Yaokang Wu, Muzi Tao, Yibo Yan, Xuezhe Ma, Taylor Berg-Kirkpatrick · 30 September 2026

  Multimodal foundation models edit natural photographs at production quality, yet the same models struggle with structured visual content such as infographics. Unlike photographs, infographics encode information through logical relations; editing one element often requires surrounding elements to be …

• DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration

  Yupeng Xie, Zhenyang Wang, Liangwei Wang, Jiayi Zhu, Zhouan Shen, Yuyu Luo · 29 September 2026

  Data videos communicate data insights through dynamic charts, voice narration, and synchronized animations, and have become a widely adopted form of data storytelling. However, producing them requires expertise in data analysis, narrative design, and video editing. Static visualization tools lack na…

• DashAct: A Progressive Diagnostic Benchmark for GUI Agents in Interactive Dashboard Analysis

  Chuhan Zhang, Qi Xie, Ziyue Wang, Jianing Yin, Yunfan Zhou, Dazhen Deng, Yingcai Wu · 29 September 2026

  Interactive dashboards require users to reveal and connect evidence across stateful interactions. Although graphical user interface (GUI) agents could automate this process, existing dashboard benchmarks primarily report final answers or task success. They provide limited insight into whether failur…

• Vibe Analysis: Exploring LLM Adoption by Data Visualization Practitioners

  Shani C Spivak, Aditi Krishna, Mahsan Nourani, Melanie Tory · 29 September 2026

  Large language models (LLMs) are enticing in their promise to support data visualization (Vis) through faster and simpler workflows for data prep, analysis, and visualization creation. Yet LLMs are notoriously error-prone and not built for data visualization tasks. Few studies have explored LLM adop…

• VG-TIE: An interpretable tabular-to-image encoding method based on visibility graphs

  David Chushig-Muzo, Luis M. L\'opez-Ramos, \'Angeles Rodr\'iguez de Cara, Eva Milara, Luis Zhinin-Vera, Diego H. Peluffo-Ord\'o\~nez · 25 September 2026

  Tabular-to-image encoding methods enable the application of models based on both convolutional neural networks and vision transformers to tabular data, transforming feature vectors into images. Existing methods employ linear and nonlinear dimensionality reduction techniques (e.g., Principal Componen…

• DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution

  Jiaming Tang, Jingxuan Wen, Liping Jing · 25 September 2026

  Multi-touch attribution (MTA) is essential for estimating the contribution of individual advertising touchpoints to user conversions. While recent studies incorporate causal inference to mitigate confounding bias from user preferences, existing multi-stage deconfounding pipelines exhibit a critical …

• PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides

  Xiaoqiu Wang, Yizhe Chi, Wenyi Li, Deyao Hong, Zhihan Shan, Mingju Gao, Kaisen Yang, Youjie Zheng, Calvin Xiao, Qinhuai Na · 25 September 2026

  Coding agents are beginning to act in the visual world. They now build webpages, GUIs, games, 3D scenes, diagrams, and documents. Success in such visual coding requires bridging two spaces: inferring visual structure and expressing it programmatically. Slides are a core medium of knowledge work, wid…

• Conversational DNA: A Visual Language and Interactive Atlas of Human and AI Dialogue

  Baihan Lin · 25 September 2026

  What makes a conversation hold together when its participants speak across one another? Topic maps offer one view, but they leave the relationships between contributions difficult to inspect. We present Conversational DNA, a visual language and interactive atlas for exploring human and AI dialogue. …

• Same Chart, Different Story: Bias in Vision-Language Chart Interpretation

  Mizanur Rahman, Huan Wu, Arash Asgari, Enamul Hoque Prince, Laleh Seyyed-Kalantari · 23 September 2026

  Vision-language models (VLMs) are increasingly used to interpret charts and generate natural-language explanations for socially consequential data. However, they may produce different narratives for the same chart when only the referenced social group changes, reinforcing stereotypes and misleading …

• Beyond Static Charts: Can Language and Vision Language Models Generate Interactive Data Visualization Interfaces?

  Mizanur Rahman, Aaryaman Kartha, Enamul Hoque Prince · 23 September 2026

  Data visualization is central to analytical reasoning, but real-world analysis increasingly requires language-driven interactive interfaces rather than static charts. Although recent large language and vision language models (LLMs/VLMs) have shown promise in generating static charts from natural lan…

• ChartJudgeBench: Evaluating LMM Judges for Chart-to-Code Generation

  Lijian Wu, Henry Hengyuan Zhao, Zijian Zhang, Jiahao Tang, Jiajun Wu, Alex Jinpeng Wang · 22 September 2026

  Building strong chart-to-code systems increasingly relies on reinforcement learning, whose effectiveness depends critically on the quality of the reward signal. Large Multimodal Models (LMMs) play a natural critical role in jointly assessing chart visual appearance and task requirements. They are th…

• LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions

  Xinnuo Zhang, Zhike Tang, Jing Xu, Haoyuan Zhao, Weikai Yang · 22 September 2026

  Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. While vision-language models (VLMs) are increasingly applied to chart understanding, their legend understanding is poorly diagnosed by aggregate accurac…

• Monitorable Chart Reasoning Agents via Verifiable Process Rewards

  Sanchit Sinha, Oana Frunza, Kashif Rasul, Aidong Zhang · 22 September 2026

  Chart reasoning agents are increasingly used to extract actionable insights in critical domains, achieving state-of-the-art performance on multiple benchmarks. Yet, high benchmark accuracy alone is insufficient for deployment, where stakeholders must be able to audit and verify how a model reaches i…

• Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents

  Srishti Palani, Vidya Setlur · 17 September 2026

  Conversational visual analytics (CVA) agents powered by large language models generate visualizations and natural-language explanations from open-ended queries. Evaluating these multimodal outputs is challenging: curated reference benchmarks are costly to author, cannot comprehensively capture the s…

• ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication

  Jiaxin Duan, Dian Jiao Shuai Zhao, Jiabing Leng, Yiran Zhang, Feng Huang · 16 September 2026

  This paper addresses the challenge of generating high-quality academic charts that match the visual standards of human-authored papers. While existing AI agents can produce well-structured text and code, their generated visualizations often lack the stylistic and semantic fidelity of human designs. …

• VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries

  Wenxin Xu, Jinwei Lu, Hwanhee Kim, Chen Jason Zhang, Xiao-Yong Wei, Haoyang Li, Yuanfeng Song · 15 September 2026

  Real-world visualization requests are routinely ambiguous, incomplete, or factually incorrect, yet existing Text-to-Visualization (Text-to-Vis) systems assume well-specified inputs and produce charts in a single pass. When queries are imperfect, a system must \emph{interact} with the user to recover…

• Inheriting the Count: How Visualization Literacy Got Its Measure

  Jos\'e Bener, Miriah Meyer · 15 September 2026

  Foundational frameworks in visualization have operationalized literacy as an individual competency, measured through chart-comprehension tasks. This focus raises a question: why has measurement become the dominant frame for understanding literacy? Rather than asking whether literacy should be measur…

• LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations

  Majd Alafrange, Samuel Friedman, John Kitonyo, Sana Tonekaboni, Mahnaz Maddah · 14 September 2026

  Latent embeddings have become a central data abstraction in modern machine learning, especially in biomedicine, where foundation models are increasingly used to encode multimodal data like clinical text, medical images, omics, and physiological signals. However, the utility and value of these repres…

• Editable Visual Design

  Junyan Ye, Wei Liu, Dongzhi Jiang, Zichen Wen, HaoDong Li, Zhutao Lv, Jiaxin Lin, Jinhua Yu, Jun He, Zilong Huang, Rui Chen, Weijia Li · 4 September 2026

  While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yields flattened bitmaps with error-prone text, precluding layer-wise post-editing. Conversely, code-based visual generation via Coding Agents provides pre…