{"total":52,"rows":[{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687,"area":null},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277,"area":null},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53,"area":null},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2210.07179","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"area":null},{"id":"2302.14794","title":"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning","created":"2023-02-28","cited_by_count":20,"area":null},{"id":"2408.03120","title":"Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baseline","created":"2024-08-06","cited_by_count":19,"area":null},{"id":"2204.04413","title":"PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization","created":"2022-04-09","cited_by_count":14,"area":null},{"id":"2303.12208","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2303.02909","title":"Dynamic Prompting: A Unified Framework for Prompt Tuning","created":"2023-03-06","cited_by_count":12,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2305.17006","title":"Zero-shot Visual Question Answering with Language Model Feedback","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2309.02155","title":"S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2205.02456","title":"Declaration-based Prompt Tuning for Visual Question Answering","created":"2022-05-05","cited_by_count":9,"area":null},{"id":"2406.17163","title":"Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errors","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2409.08518","title":"Anytime Continual Learning for Open Vocabulary Classification","created":"2024-09-13","cited_by_count":8,"area":null},{"id":"2203.03195","title":"Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2210.13076","title":"Towards Unifying Reference Expression Generation and Comprehension","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2211.09371","title":"CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge","created":"2022-11-17","cited_by_count":5,"area":null},{"id":"2312.04793","title":"User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2506.21237","title":"DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2307.07742","title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","created":"2023-07-15","cited_by_count":4,"area":null},{"id":"2310.05109","title":"Lightweight In-Context Tuning for Multimodal Unified Models","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2311.03320","title":"Tackling Concept Shift in Text Classification using Entailment-style Modeling","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2403.07246","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2210.17238","title":"Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2406.00334","title":"Image Captioning via Dynamic Path Customization","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2303.02411","title":"The Contribution of Knowledge in Visiolinguistic Learning: A Survey on Tasks and Challenges","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2308.02862","title":"Improving Generalization of Image Captioning with Unsupervised Prompt Learning","created":"2023-08-05","cited_by_count":2,"area":null},{"id":"2308.16269","title":"Can Prompt Learning Benefit Radiology Report Generation?","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2501.00398","title":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","created":"2024-12-31","cited_by_count":2,"area":null},{"id":"2506.10912","title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2306.00409","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2505.18754","title":"Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2507.14544","title":"Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2509.20871","title":"SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2603.15909","title":"Prompt Engineering for Scale Development in Generative Psychometrics","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2309.15487","title":"Tackling VQA with Pretrained Foundation Models without Further Training","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2310.02528","title":"On the Cognition of Visual Question Answering Models and Human Intelligence: A Comparative Study","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2310.10219","title":"Using Global Land Cover Product as Prompt for Cropland Mapping via Visual Foundation Model","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2501.06546","title":"Natural Language Supervision for Low-light Image Enhancement","created":"2025-01-11","cited_by_count":0,"area":null},{"id":"2501.07221","title":"Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2505.20097","title":"S2LPP: Small-to-Large Prompt Prediction across LLMs","created":"2025-05-26","cited_by_count":0,"area":null}],"next_cursor":null}