{"total":16,"rows":[{"id":"2412.00947","title":"VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information","created":"2024-12-01","cited_by_count":39,"area":"mllm"},{"id":"2510.22391","title":"Top-Down Semantic Refinement for Image Captioning","created":"2025-10-25","cited_by_count":16,"area":"mllm"},{"id":"2511.17722","title":"Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions","created":"2025-11-21","cited_by_count":6,"area":"mllm"},{"id":"2605.22903","title":"Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?","created":"2026-05-21","cited_by_count":6,"area":"mllm"},{"id":"2502.04389","title":"Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions","created":"2025-02-05","cited_by_count":2,"area":"mllm"},{"id":"2603.02865","title":"Nodes Are Early, Edges Are Late: Probing Diagram Representations in Large Vision-Language Models","created":"2026-03-03","cited_by_count":1,"area":"mllm"},{"id":"2509.08266","title":"Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features","created":"2025-09-10","cited_by_count":0,"area":"mllm"},{"id":"2511.13225","title":"Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms","created":"2025-11-17","cited_by_count":0,"area":"mllm"},{"id":"2511.20162","title":"Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection","created":"2025-11-25","cited_by_count":0,"area":"mllm"},{"id":"2602.11678","title":"Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing","created":"2026-02-12","cited_by_count":0,"area":"mllm"},{"id":"2602.13376","title":"An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation","created":"2026-02-13","cited_by_count":0,"area":"mllm"},{"id":"2605.15672","title":"VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following","created":"2026-05-15","cited_by_count":0,"area":"mllm"},{"id":"2607.02853","title":"Prior Bias in Vision Language Models on UML Diagram Interpretation","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2607.24707","title":"ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2609.35272","title":"When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.04721","title":"Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models","created":"2026-10-03","cited_by_count":0,"area":"mllm"}],"next_cursor":null}