DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

arXiv:2610.11993 · cs.CV, cs.AI, cs.CL · Submitted 2026-10-08 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/HKUSTDial/DataVista

Terminology

• Accuracy — 59× in this paper · explained in 1 episode
• Benchmark — 45× in this paper · explained in 2 episodes
• Temporal Reasoning — 26× in this paper · explained in 2 episodes
• Causal Reasoning — 16× in this paper · explained in 2 episodes
• Benchmarking — 8× in this paper · explained in 3 episodes
• Aggregation — 6× in this paper · explained in 1 episode
• Verification — 6× in this paper · explained in 2 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Core — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Text-to-SQL — 3× in this paper · explained in 3 episodes
• Commentary — 2× in this paper · explained in 2 episodes
• Cognitive Load — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation
• HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding
• Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
• VisTR: Visualizations as Representations for Time-series Table Reasoning
• DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
• VideoAesBench: Benchmarking the Video Aesthetics Perception Capabilities of Large Multimodal Models
• nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
• Exploring Agentic Visual Analytics: A Co-Evolutionary Framework of Roles and Workflows
• Neptune: The Long Orbit to Benchmarking Long Video Understanding
• Data Playwright: Authoring Data Videos with Annotated Narration
• How Does Empirical Research Facilitate Creation Tool Design? A Data Video Perspective
• DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning
• IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation
• sketch-plot: Progressive Editing for Text-to-Image Academic Figures
• ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
• Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation
• TableTale: Reviving the Narrative Interplay Between Data Tables and Text in Scientific Papers
• LVBench: An Extreme Long Video Understanding Benchmark

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models