# Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editing

arXiv: https://arxiv.org/abs/2609.08657 · HTML: https://mlsanity.com/paper/2609.08657/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)
- [MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning](https://mlsanity.com/paper/2311.10774/) (2023)
- [MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering](https://mlsanity.com/paper/2212.09662/) (2022)
- [ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation](https://mlsanity.com/paper/2406.09961/) (2024)
- [ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning](https://mlsanity.com/paper/2402.12185/) (2024)
- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering](https://mlsanity.com/paper/2504.05506/) (2025)
- [ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing](https://mlsanity.com/paper/2505.11935/) (2025)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules](https://mlsanity.com/paper/2304.02173/) (2023)
- [StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding](https://mlsanity.com/paper/2309.11268/) (2023)
- [ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation](https://mlsanity.com/paper/2505.18668/) (2025)
- [PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks](https://mlsanity.com/paper/2606.13108/) (2026)
- [RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning](https://mlsanity.com/paper/2503.23131/) (2025)
- [ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing](https://mlsanity.com/paper/2511.15266/) (2025)
- [Charts Are Not Images: On the Challenges of Scientific Chart Editing](https://mlsanity.com/paper/2512.00752/) (2025)
- [ChartM3: Benchmarking Chart Editing with Multimodal Instructions](https://mlsanity.com/paper/2507.21167/) (2025)
- [ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models](https://mlsanity.com/paper/2602.15758/) (2026)
- [ChartE3: A Comprehensive Benchmark for End-to-End Chart Editing](https://mlsanity.com/paper/2601.21694/) (2026)
- [START: Spatial and Textual Learning for Chart Understanding](https://mlsanity.com/paper/2512.07186/) (2025)
- [ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing](https://mlsanity.com/paper/2607.10301/) (2026)
- [ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring](https://mlsanity.com/paper/2605.07415/) (2026)
- [PaintBench: Deterministic Evaluation of Precise Visual Editing](https://mlsanity.com/paper/2606.00188/) (2026)

## Abstract (arXiv)

Charts are structured visual compositions whose elements have distinct functional roles, semantic correspondences, and visibility relations. This structural view motivates evaluating whether models can understand and manipulate charts at the layer level. Existing chart benchmarks, however, primarily assess the correctness or fidelity of final outputs and do not directly evaluate these layer-wise behaviors. We present LayerWiseBench, a benchmark organized around three core concepts, layer attribution, layer binding, and visibility ordering, that structure its chart-understanding and chart-editing evaluations. Generated from executable chart programs, LayerWiseBench pairs each rendered chart with spatially aligned per-layer RGBA assets and construction-derived labels for functional roles, semantic bindings, and visibility relations. From this layer-wise representation, we derive controlled understanding questions, editing targets, reference images, and evaluation regions. It contains 2,800 source charts across 14 chart paradigms, from which we derive 7,329 layer-wise understanding questions and 53,791 instruction-guided editing variants. Among the evaluated VLMs, Qwen3.5-27B, which achieves the highest QA macro-average, obtains 93.04% accuracy on layer attribution and 97.46% on layer binding, but only 61.46% on visibility ordering. Across the four evaluated image editors, overall mIoU ranges from 1.49% to 4.93%, and visibility-constrained edits have the lowest mIoU for every editor, ranging from 0.37% to 2.00%. Taken together, these results identify tasks involving front-to-back relations between overlapping components as a recurring challenge across understanding and editing, motivating more explicit modeling of component identity and visibility relations.