mlsanityData to 7 Oct 2026

Chart understanding and anomaly detection

396 papers3 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: chart, anomaly, reasoning, visual, anomaly detection

Key facts. Chart understanding and anomaly detection: 396 papers on arXiv since 2022 (data through 7 Oct 2026). 32 of its 396 mapped papers (8%) cite “ChartLlama: A Multimodal LLM for Chart Understanding and Generation” (2023, arXiv 2311.16483). 30 of its 396 mapped papers (8%) cite “CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs” (2024, arXiv 2406.18521). 12 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

12 new papers, 17 Sep – 7 Oct; 3 this week.

  1. This week · 3
  2. TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity
  3. ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications
  4. CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs also fits: VLM benchmarks and visual reasoning
  5. Earlier · 9
  6. Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models
  7. OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software also fits: Embodied and 3D vision-language models
  8. TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization
  9. ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density
  10. K-OPSD: Verifiable On-Policy Self-Distillation for Post-Training Vision-Language Models on AEC Drawings also fits: Embodied and 3D vision-language models
  11. Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line Inspection also fits: VLM benchmarks and visual reasoning
  12. Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy also fits: Medical vision-language models
All 12
  1. PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design also fits: Embodied and 3D vision-language models
  2. Adapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection also fits: Embodied and 3D vision-language models

Foundations

Most cited by papers here

  1. ChartLlama: A Multimodal LLM for Chart Understanding and Generation2023cited by 32 here
  2. CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs2024cited by 30 here
  3. MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering2022cited by 28 here
  4. ChartBench: A Benchmark for Complex Visual Reasoning in Charts2023cited by 27 here
  5. UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning2023cited by 25 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 12 here
  2. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 23 here
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 24 here
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 25 here
  5. 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMscited by 30 here
  6. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 22 here
18 more it builds on, not in this chain
  1. 2022MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derenderingcited by 28 here
  2. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 25 here
  3. 2023A Survey on Multimodal Large Language Modelscited by 12 here
  4. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 21 here
  5. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 17 here
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 23 here
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 42 here
  8. 2023MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuningcited by 23 here
  9. 2023ChartLlama: A Multimodal LLM for Chart Understanding and Generationcited by 32 here
  10. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 33 here
  11. 2023ChartBench: A Benchmark for Complex Visual Reasoning in Chartscited by 27 here
  12. 2024ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuningcited by 19 here
  13. 2024ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoningcited by 23 here
  14. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 14 here
  15. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 20 here
  16. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 27 here
  17. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 13 here
  18. 2025Qwen3-VL Technical Reportcited by 13 here

The 24 most cited of 616.

Browse

30 of 396, ranked 6–35

  1. 6ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning202423
  2. 7MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning202323
  3. 8ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning202419
  4. 9AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models202317
  5. 10ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation202412
  6. 11VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection202312
  7. 12Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset202411
  8. 13Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models202510
  9. 14ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering202410
  10. 15ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation20259
All 30
  1. 16Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM20248
  2. 17Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning20248
  3. 18FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation20257
  4. 19Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering20247
  5. 20Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs20247
  6. 21How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?20247
  7. 22Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection20237
  8. 23Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning20237
  9. 24ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models20256
  10. 25Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots20246
  11. 26Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs20246
  12. 27ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area20246
  13. 28Distill Visual Chart Reasoning Ability from LLMs to MLLMs20246
  14. 29VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models20246
  15. 30MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems20245
  16. 31Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity20245
  17. 32Can Multimodal LLMs Perform Time Series Anomaly Detection?20254
  18. 33Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering20254
  19. 34ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing20254
  20. 35FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models20244