{"total":15,"rows":[{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2310.16781","title":"Kiki or Bouba? Sound Symbolism in Vision-and-Language Models","created":"2023-10-25","cited_by_count":14,"area":null},{"id":"2407.17974","title":"What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language models","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2309.02691","title":"A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2405.14863","title":"A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2409.08199","title":"AudioBERT: Audio Knowledge Augmented Language Model","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2503.16853","title":"Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2509.17641","title":"AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2403.01306","title":"ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation","created":"2024-03-02","cited_by_count":0,"area":null},{"id":"2409.11148","title":"Improving the Efficiency of Visually Augmented Language Models","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2510.21842","title":"Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2610.19443","title":"More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}