{"total":20,"rows":[{"id":"2410.05160","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","created":"2024-10-07","cited_by_count":228,"area":"mllm"},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2402.07270","title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy","created":"2024-02-11","cited_by_count":26,"area":"mllm"},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24,"area":"mllm"},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19,"area":"mllm"},{"id":"2403.04735","title":"SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM","created":"2024-03-07","cited_by_count":18,"area":"mllm"},{"id":"2407.03000","title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values","created":"2024-07-03","cited_by_count":12,"area":"mllm"},{"id":"2601.06843","title":"Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models","created":"2026-01-11","cited_by_count":8,"area":"mllm"},{"id":"2406.00980","title":"Selectively Answering Visual Questions","created":"2024-06-03","cited_by_count":5,"area":"mllm"},{"id":"2512.19537","title":"Event Extraction in Large Language Model","created":"2025-12-22","cited_by_count":5,"area":"mllm"},{"id":"2310.05060","title":"DeVAn: Dense Video Annotation for Video-Language Models","created":"2023-10-08","cited_by_count":3,"area":"mllm"},{"id":"2506.14808","title":"PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models","created":"2025-06-03","cited_by_count":3,"area":"mllm"},{"id":"2510.00041","title":"Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness","created":"2025-09-27","cited_by_count":2,"area":"mllm"},{"id":"2605.23694","title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","created":"2026-05-22","cited_by_count":2,"area":"mllm"},{"id":"2411.02589","title":"Context-Informed Machine Translation of Manga using Multimodal Large Language Models","created":"2024-11-04","cited_by_count":1,"area":"mllm"},{"id":"2510.25413","title":"Seeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Media","created":"2025-10-29","cited_by_count":0,"area":"mllm"},{"id":"2608.00235","title":"Attention-Steered Vision-Language Models for Sign Language Translation","created":"2026-07-31","cited_by_count":0,"area":"mllm"},{"id":"2608.11534","title":"CT-$\\Delta$Bench: A Benchmark for Longitudinal 3D Medical Imaging Difference Reporting with Vision-Language Models","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2609.01772","title":"MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal Models","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2610.20461","title":"Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}