{"total":20,"rows":[{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2206.00100","title":"VALHALLA: Visual Hallucination for Machine Translation","created":"2022-05-31","cited_by_count":27,"area":null},{"id":"2204.10931","title":"MCSE: Multimodal Contrastive Learning of Sentence Embeddings","created":"2022-04-22","cited_by_count":22,"area":null},{"id":"2204.08535","title":"Imagination-Augmented Natural Language Understanding","created":"2022-04-18","cited_by_count":19,"area":null},{"id":"2109.11321","title":"Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?","created":"2021-09-23","cited_by_count":18,"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":"2308.02541","title":"Towards More Human-like AI Communication: A Review of Emergent Communication Research","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2401.10222","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2104.07500","title":"Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Training","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2103.13942","title":"Visual Grounding Strategies for Text-Only Natural Language Processing","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2106.08648","title":"Semantic sentence similarity: size does not always matter","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2206.08823","title":"Language with Vision: a Study on Grounded Word and Sentence Embeddings","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2312.01592","title":"Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment","created":"2023-12-04","cited_by_count":5,"area":null},{"id":"2202.10292","title":"Seeing the advantage: visually grounding word embeddings to better capture human semantic knowledge","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2206.11953","title":"Do Trajectories Encode Verb Meaning?","created":"2022-06-23","cited_by_count":2,"area":null},{"id":"2508.07264","title":"FLUID: Flow-Latent Unified Integration via Token Distillation for Expert Specialization in Multimodal Learning","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2206.15381","title":"How direct is the link between words and images?","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2210.05487","title":"Like a bilingual baby: The advantage of visually grounding a bilingual language model","created":"2022-10-11","cited_by_count":0,"area":null}],"next_cursor":null}