HistGramBench: Measuring Structural Recovery When Multimodal Models Redraw Historical Mathematical Diagrams as TikZ
cs.CV, cs.CL, cs.DL
Submitted: 2026-10-18
Updated: 2026-10-18
Terminology
Sources
- Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
- PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
- VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
- GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language
- Ministral 3
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
- NVIDIA Nemotron Nano V2 VL
- Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
- FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs