{"total":13,"rows":[{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293,"area":"lr"},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254,"area":"lr"},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2406.19131","title":"CELLO: Causal Evaluation of Large Vision-Language Models","created":"2024-06-27","cited_by_count":10,"area":"lr"},{"id":"2503.01891","title":"MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems","created":"2025-02-27","cited_by_count":10,"area":"lr"},{"id":"2503.23137","title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","created":"2025-03-29","cited_by_count":5,"area":"lr"},{"id":"2505.15576","title":"Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models","created":"2025-05-21","cited_by_count":2,"area":"lr"},{"id":"2510.16540","title":"Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"id":"2507.13405","title":"COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark","created":"2025-07-17","cited_by_count":1,"area":"lr"},{"id":"2607.27670","title":"JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2605.29951","title":"MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2607.16094","title":"How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2609.31456","title":"Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}