{"total":14,"rows":[{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75,"area":null},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2505.19240","title":"LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2406.04886","title":"Unveiling the Invisible: Captioning Videos with Metaphors","created":"2024-06-07","cited_by_count":7,"area":null},{"id":"2310.10543","title":"ViPE: Visualise Pretty-much Everything","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2503.15358","title":"SemEval-2025 Task 1: AdMIRe -- Advancing Multimodal Idiomaticity Representation","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2505.11237","title":"Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2601.08645","title":"A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2606.05109","title":"RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.04750","title":"Simile Understanding in Text-to-Image Models: An Evaluation Framework","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}