{"total":20,"rows":[{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529,"area":"lr"},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127,"area":"lr"},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66,"area":"lr"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2410.14690","title":"Rethinking VLMs and LLMs for Image Classification","created":"2024-10-03","cited_by_count":12,"area":"lr"},{"id":"2603.03975","title":"Phi-4-reasoning-vision-15B Technical Report","created":"2026-03-04","cited_by_count":10,"area":"lr"},{"id":"2410.09220","title":"M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought","created":"2024-10-11","cited_by_count":9,"area":"lr"},{"id":"2310.10418","title":"Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms","created":"2023-10-16","cited_by_count":8,"area":"lr"},{"id":"2510.08630","title":"ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection","created":"2025-10-08","cited_by_count":8,"area":"lr"},{"id":"2506.18919","title":"From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment","created":"2025-06-15","cited_by_count":4,"area":"lr"},{"id":"2603.01225","title":"Can Thinking Models Think to Detect Hateful Memes?","created":"2026-03-01","cited_by_count":2,"area":"lr"},{"id":"2204.10521","title":"Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem","created":"2022-04-22","cited_by_count":1,"area":"lr"},{"id":"2506.22036","title":"Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion","created":"2025-06-27","cited_by_count":1,"area":"lr"},{"id":"2507.21924","title":"MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning","created":"2025-07-29","cited_by_count":1,"area":"lr"},{"id":"2603.19744","title":"Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM Benchmarking","created":"2026-03-20","cited_by_count":0,"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":"2607.15442","title":"Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2607.24082","title":"Towards High-Level Semantic Intelligence","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2608.27176","title":"When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2610.01917","title":"MoLE: Mixture of Latent Experts for Complementary Visual Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}