{"total":78,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53,"area":null},{"id":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2105.14462","title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","created":"2021-05-30","cited_by_count":44,"area":null},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39,"area":null},{"id":"2110.08182","title":"The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color","created":"2021-10-15","cited_by_count":32,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2210.03765","title":"Visualize Before You Write: Imagination-Guided Open-Ended Text Generation","created":"2022-10-07","cited_by_count":30,"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":"2109.10246","title":"Does Vision-and-Language Pretraining Improve Lexical Grounding?","created":"2021-09-21","cited_by_count":25,"area":null},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23,"area":null},{"id":"2204.10931","title":"MCSE: Multimodal Contrastive Learning of Sentence Embeddings","created":"2022-04-22","cited_by_count":22,"area":null},{"id":"2105.13073","title":"Maria: A Visual Experience Powered Conversational Agent","created":"2021-05-27","cited_by_count":19,"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":"2205.10178","title":"Visually-Augmented Language Modeling","created":"2022-05-20","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":"2305.04572","title":"Putting Natural in Natural Language Processing","created":"2023-05-08","cited_by_count":17,"area":null},{"id":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14,"area":null},{"id":"2504.19267","title":"VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?","created":"2025-04-27","cited_by_count":11,"area":null},{"id":"2203.07519","title":"Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2402.14304","title":"Vision-Language Navigation with Embodied Intelligence: A Survey","created":"2024-02-22","cited_by_count":9,"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":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2211.11701","title":"Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2305.16944","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2210.05991","title":"Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2403.14551","title":"Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling","created":"2024-03-21","cited_by_count":6,"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":"2212.07937","title":"Visually-augmented pretrained language models for NLP tasks without images","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2507.04886","title":"Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2209.08982","title":"How to Adapt Pre-trained Vision-and-Language Models to a Text-only Input?","created":"2022-09-19","cited_by_count":4,"area":null},{"id":"2306.02348","title":"Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2403.07301","title":"Let Storytelling Tell Vivid Stories: An Expressive and Fluent Multimodal Storyteller","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2504.00942","title":"Experiential Semantic Information and Brain Alignment: Are Multimodal Models Better than Language Models?","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2210.05836","title":"CLIP also Understands Text: Prompting CLIP for Phrase Understanding","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2211.04576","title":"Detecting Euphemisms with Literal Descriptions and Visual Imagery","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2212.13428","title":"A Survey on Knowledge-Enhanced Pre-trained Language Models","created":"2022-12-27","cited_by_count":3,"area":null},{"id":"2403.03075","title":"Detecting Concrete Visual Tokens for Multimodal Machine Translation","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2204.07316","title":"XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding","created":"2022-04-15","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2212.00281","title":"Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2305.07358","title":"Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2312.03025","title":"Training on Synthetic Data Beats Real Data in Multimodal Relation Extraction","created":"2023-12-05","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":"2205.01941","title":"Lexical Knowledge Internalization for Neural Dialog Generation","created":"2022-05-04","cited_by_count":1,"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":"2307.02615","title":"Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition","created":"2023-07-05","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":"2412.00684","title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding","created":"2024-12-01","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":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"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":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2212.03864","title":"Can Offline Reinforcement Learning Help Natural Language Understanding?","created":"2022-09-15","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","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":"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":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2608.19529","title":"When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models","created":"2026-08-20","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}