When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning

arXiv:2609.39142 · cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/yunbeizhang/text-for-vision

Terminology

• Accuracy — 28× in this paper · explained in 1 episode
• Fidelity — 27× in this paper · explained in 2 episodes
• AUC — 7× in this paper · explained in 2 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Multimodal Reasoning — 3× in this paper · explained in 5 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• International Conference on Document Analysis and Recognition — 1× in this paper
• Provenance — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes
• Winter Conference on Applications of Computer Vision — 1× in this paper

Sources

• Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
• ICDAR 2019 Competition on Scene Text Visual Question Answering
• OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
• The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
• Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
• DISSECT: Diagnosing Where Vision Ends and Language Priors Begin in Scientific VLMs
• Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
• Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
• RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion with Matrix-Valued Trust for Multimodal Prediction under Modality Uncertainty
• MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
• Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
• Stop Comparing LLM Agents Without Disclosing the Harness

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