IVG combines spec-grounded introspection and view-grounded interaction to let VLMs achieve 0.81 QA accuracy on interactive charts, with gains on overlapping elements, using a new benchmark of 500 Plotly figures.
InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13872–13882
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
chart-plot is an agentic harness using style-aware code generation from venue figures, a LaTeX-aware render-and-revise loop, and structured edit handles to produce top-venue-ready academic charts.
A structured survey of multimodal code intelligence that formulates the field by code roles and organizes work into four domains while proposing verification-centered research directions.
citing papers explorer
-
Beyond Pixels: Introspective and Interactive Grounding for Visualization Agents
IVG combines spec-grounded introspection and view-grounded interaction to let VLMs achieve 0.81 QA accuracy on interactive charts, with gains on overlapping elements, using a new benchmark of 500 Plotly figures.
-
Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation
chart-plot is an agentic harness using style-aware code generation from venue figures, a LaTeX-aware render-and-revise loop, and structured edit handles to produce top-venue-ready academic charts.
-
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
A structured survey of multimodal code intelligence that formulates the field by code roles and organizes work into four domains while proposing verification-centered research directions.