{"total":126,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"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":"2301.00303","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","created":"2022-12-31","cited_by_count":145,"area":"lr"},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123,"area":"mllm"},{"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":"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":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2210.03809","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","created":"2022-10-07","cited_by_count":94,"area":"rag"},{"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":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69,"area":null},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65,"area":"mllm"},{"id":"2407.12735","title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge","created":"2024-07-17","cited_by_count":62,"area":"mllm"},{"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":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2404.15736","title":"What Makes Multimodal In-Context Learning Work?","created":"2024-04-24","cited_by_count":56,"area":null},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51,"area":"lr"},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51,"area":"rag"},{"id":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42,"area":"mllm"},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36,"area":null},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"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":"2405.00175","title":"Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models","created":"2024-04-30","cited_by_count":23,"area":"rag"},{"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":"2409.09510","title":"Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models","created":"2024-09-14","cited_by_count":21,"area":null},{"id":"2204.06644","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","created":"2022-04-13","cited_by_count":20,"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":"2311.09050","title":"Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts","created":"2023-11-15","cited_by_count":20,"area":"lr"},{"id":"2503.18491","title":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","created":"2025-03-24","cited_by_count":19,"area":"mllm"},{"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":"2403.04735","title":"SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM","created":"2024-03-07","cited_by_count":18,"area":"mllm"},{"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":"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":"2404.07078","title":"VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning","created":"2024-04-10","cited_by_count":16,"area":"lr"},{"id":"2502.04176","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","created":"2025-02-06","cited_by_count":15,"area":"rag"},{"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":"2310.13570","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","created":"2023-10-20","cited_by_count":14,"area":null},{"id":"2410.09942","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","created":"2024-10-13","cited_by_count":14,"area":"rag"},{"id":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2502.16641","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","created":"2025-02-23","cited_by_count":13,"area":"rag"},{"id":"2312.04837","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","created":"2023-12-08","cited_by_count":12,"area":"distill"},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"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":"2311.17331","title":"Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering","created":"2023-11-29","cited_by_count":11,"area":"lr"},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","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":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","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":"2405.03373","title":"Knowledge-aware Text-Image Retrieval for Remote Sensing Images","created":"2024-05-06","cited_by_count":9,"area":null},{"id":"2306.08129","title":"AVIS: Autonomous Visual Information Seeking with Large Language Model Agent","created":"2023-06-13","cited_by_count":8,"area":"agents"},{"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},{"id":"2210.10176","title":"Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering","created":"2022-10-18","cited_by_count":7,"area":null},{"id":"2305.18373","title":"KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models","created":"2023-05-28","cited_by_count":7,"area":"lr"},{"id":"2404.05465","title":"HAMMR: HierArchical MultiModal React agents for generic VQA","created":"2024-04-08","cited_by_count":7,"area":"agents"},{"id":"2506.07785","title":"Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger","created":"2025-06-09","cited_by_count":7,"area":"lr"},{"id":"2304.03754","title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","created":"2023-04-07","cited_by_count":6,"area":null},{"id":"2407.12277","title":"Multimodal Reranking for Knowledge-Intensive Visual Question Answering","created":"2024-07-17","cited_by_count":6,"area":null},{"id":"2305.00970","title":"ArK: Augmented Reality with Knowledge Interactive Emergent Ability","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2305.13782","title":"Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2403.18252","title":"Beyond Embeddings: The Promise of Visual Table in Visual Reasoning","created":"2024-03-27","cited_by_count":5,"area":"lr"},{"id":"2404.13947","title":"Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering","created":"2024-04-22","cited_by_count":5,"area":"mllm"},{"id":"2502.18536","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","created":"2025-02-25","cited_by_count":5,"area":"rag"},{"id":"2508.00955","title":"From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2308.15851","title":"Prompting Vision Language Model with Knowledge from Large Language Model for Knowledge-Based VQA","created":"2023-08-30","cited_by_count":4,"area":"mllm"},{"id":"2403.07078","title":"Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2404.10226","title":"Find The Gap: Knowledge Base Reasoning For Visual Question Answering","created":"2024-04-16","cited_by_count":4,"area":"lr"},{"id":"2409.18996","title":"From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models","created":"2024-09-19","cited_by_count":4,"area":"lr"},{"id":"2301.10799","title":"Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2401.10712","title":"Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge","created":"2024-01-19","cited_by_count":3,"area":"lr"},{"id":"2403.10037","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","created":"2024-03-15","cited_by_count":3,"area":"lr"},{"id":"2409.07331","title":"Learning to Compress Contexts for Efficient Knowledge-based Visual Question Answering","created":"2024-09-11","cited_by_count":3,"area":"mllm"},{"id":"2410.19144","title":"Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistant","created":"2024-10-24","cited_by_count":3,"area":"mllm"},{"id":"2411.08334","title":"MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrieval","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2412.18351","title":"Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering","created":"2024-12-24","cited_by_count":3,"area":"agents"},{"id":"2506.06962","title":"AR-RAG: Autoregressive Retrieval Augmentation for Image Generation","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2205.11686","title":"On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization","created":"2022-05-24","cited_by_count":2,"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":"2310.08148","title":"Open-Set Knowledge-Based Visual Question Answering with Inference Paths","created":"2023-10-12","cited_by_count":2,"area":"lr"},{"id":"2406.09994","title":"Precision Empowers, Excess Distracts: Visual Question Answering With Dynamically Infused Knowledge In Language Models","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2406.18839","title":"Disentangling Knowledge-based and Visual Reasoning by Question Decomposition in KB-VQA","created":"2024-06-27","cited_by_count":2,"area":"lr"},{"id":"2502.20964","title":"Fine-Grained Knowledge Structuring and Retrieval for Visual Question Answering","created":"2025-02-28","cited_by_count":2,"area":"rag"},{"id":"2504.04065","title":"Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering","created":"2025-04-05","cited_by_count":2,"area":"rag"},{"id":"2511.11132","title":"From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2601.19060","title":"Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2603.05256","title":"Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum","created":"2026-03-05","cited_by_count":2,"area":"lr"},{"id":"2302.05608","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","created":"2023-02-11","cited_by_count":1,"area":null},{"id":"2306.01144","title":"Evaluating the Capabilities of Multi-modal Reasoning Models with Synthetic Task Data","created":"2023-06-01","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}