{"total":164,"rows":[{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347,"area":null},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320,"area":null},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267,"area":null},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2302.11713","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","created":"2023-02-23","cited_by_count":207,"area":null},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155,"area":null},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126,"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":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"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":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2303.01248","title":"Can ChatGPT Assess Human Personalities? A General Evaluation Framework","created":"2023-03-01","cited_by_count":70,"area":null},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69,"area":null},{"id":"2308.03349","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","created":"2023-08-07","cited_by_count":68,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2206.01201","title":"REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering","created":"2022-06-02","cited_by_count":59,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2404.15736","title":"What Makes Multimodal In-Context Learning Work?","created":"2024-04-24","cited_by_count":56,"area":null},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","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":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2407.20727","title":"SceneTeller: Language-to-3D Scene Generation","created":"2024-07-30","cited_by_count":43,"area":null},{"id":"2505.21494","title":"Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment","created":"2025-05-27","cited_by_count":43,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"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":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"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":"2303.05063","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","created":"2023-03-09","cited_by_count":38,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36,"area":null},{"id":"2203.08055","title":"Modular and Parameter-Efficient Multimodal Fusion with Prompting","created":"2022-03-15","cited_by_count":35,"area":null},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2301.10939","title":"Affective Faces for Goal-Driven Dyadic Communication","created":"2023-01-26","cited_by_count":35,"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":"2402.06475","title":"Large Language Models for Captioning and Retrieving Remote Sensing Images","created":"2024-02-09","cited_by_count":30,"area":null},{"id":"2306.01183","title":"Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2109.08029","title":"Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering","created":"2021-09-15","cited_by_count":25,"area":null},{"id":"2310.07652","title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","created":"2023-10-11","cited_by_count":25,"area":null},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25,"area":null},{"id":"2310.13590","title":"ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction","created":"2023-10-20","cited_by_count":24,"area":null},{"id":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23,"area":null},{"id":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","cited_by_count":23,"area":null},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2208.10159","title":"Prompt-Matched Semantic Segmentation","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2306.16762","title":"Unified Language Representation for Question Answering over Text, Tables, and Images","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2207.12888","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","created":"2022-07-26","cited_by_count":18,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2404.08589","title":"Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts","created":"2024-04-12","cited_by_count":18,"area":null},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2310.07328","title":"An Empirical Study of Instruction-tuning Large Language Models in Chinese","created":"2023-10-11","cited_by_count":17,"area":null},{"id":"2305.05138","title":"Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media","created":"2023-05-09","cited_by_count":16,"area":null},{"id":"2305.18842","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2306.04308","title":"Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality","created":"2023-06-07","cited_by_count":16,"area":null},{"id":"2402.12728","title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2304.13649","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2308.16753","title":"Context Aware Query Rewriting for Text Rankers using LLM","created":"2023-08-31","cited_by_count":14,"area":null},{"id":"2310.13570","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","created":"2023-10-20","cited_by_count":14,"area":null},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2411.16313","title":"CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning","created":"2024-11-25","cited_by_count":14,"area":null},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2310.08027","title":"Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection","created":"2023-10-12","cited_by_count":13,"area":null},{"id":"2203.03878","title":"HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks","created":"2022-03-08","cited_by_count":12,"area":null},{"id":"2211.15521","title":"G^3: Geolocation via Guidebook Grounding","created":"2022-11-28","cited_by_count":12,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2305.12212","title":"Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge","created":"2023-05-20","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":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2402.11750","title":"In-Context Learning Demonstration Selection via Influence Analysis","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","cited_by_count":11,"area":null},{"id":"2306.16478","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2310.02161","title":"Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2311.12890","title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2408.00447","title":"DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration","created":"2024-08-01","cited_by_count":10,"area":null},{"id":"2509.18436","title":"Memory-QA: Answering Recall Questions Based on Multimodal Memories","created":"2025-09-22","cited_by_count":10,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2307.09909","title":"Chit-Chat or Deep Talk: Prompt Engineering for Process Mining","created":"2023-07-19","cited_by_count":9,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2402.10977","title":"Generative AI and Process Systems Engineering: The Next Frontier","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2412.16936","title":"Rationale-guided Prompting for Knowledge-based Visual Question Answering","created":"2024-12-22","cited_by_count":9,"area":null},{"id":"2112.06888","title":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2407.15346","title":"Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models","created":"2024-07-22","cited_by_count":8,"area":null}],"next_cursor":"100"}