{"total":26,"rows":[{"id":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44,"area":null},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40,"area":null},{"id":"2205.12247","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","created":"2022-05-24","cited_by_count":30,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2204.08535","title":"Imagination-Augmented Natural Language Understanding","created":"2022-04-18","cited_by_count":19,"area":null},{"id":"2305.14057","title":"Can Language Models Understand Physical Concepts?","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2210.12261","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2403.05468","title":"Will GPT-4 Run DOOM?","created":"2024-03-08","cited_by_count":6,"area":null},{"id":"2212.07937","title":"Visually-augmented pretrained language models for NLP tasks without images","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2307.05610","title":"Substance or Style: What Does Your Image Embedding Know?","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2402.17213","title":"VCD: A Dataset for Visual Commonsense Discovery in Images","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2305.15028","title":"ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2310.05481","title":"Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2402.15337","title":"Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning Strategies","created":"2024-02-23","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":"2304.10311","title":"Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2402.11710","title":"A Note on Bias to Complete","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2402.13584","title":"WinoViz: Probing Visual Properties of Objects Under Different States","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2403.13666","title":"Grounding Spatial Relations in Text-Only Language Models","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","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":"2409.11148","title":"Improving the Efficiency of Visually Augmented Language Models","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2509.15277","title":"Copycat vs. Original: Multi-modal Pretraining and Variable Importance in Box-office Prediction","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.19269","title":"Extracting Conceptual Spaces from LLMs Using Prototype Embeddings","created":"2025-09-23","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}],"next_cursor":null}