{"total":59,"rows":[{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"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":"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":"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":"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":"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":"2404.15736","title":"What Makes Multimodal In-Context Learning Work?","created":"2024-04-24","cited_by_count":56,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"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":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2311.16432","title":"Text-Driven Image Editing via Learnable Regions","created":"2023-11-28","cited_by_count":31,"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":"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":"2411.09273","title":"Cross-Modal Consistency in Multimodal Large Language Models","created":"2024-11-14","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":"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":"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":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2403.17237","title":"DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion","created":"2024-03-25","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":"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":"2402.10977","title":"Generative AI and Process Systems Engineering: The Next Frontier","created":"2024-02-15","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":"2211.16504","title":"Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles","created":"2022-11-29","cited_by_count":7,"area":"mllm"},{"id":"2404.05465","title":"HAMMR: HierArchical MultiModal React agents for generic VQA","created":"2024-04-08","cited_by_count":7,"area":"agents"},{"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":"2507.12441","title":"Describe Anything Model for Visual Question Answering on Text-rich Images","created":"2025-07-16","cited_by_count":5,"area":"mllm"},{"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":"2412.09612","title":"Olympus: A Universal Task Router for Computer Vision Tasks","created":"2024-12-12","cited_by_count":4,"area":"mllm"},{"id":"2310.09285","title":"SAIR: Learning Semantic-aware Implicit Representation","created":"2023-10-13","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":"2603.00511","title":"Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning","created":"2026-02-28","cited_by_count":3,"area":"rag"},{"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":"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":"2508.07023","title":"MV-CoRe: Multimodal Visual-Conceptual Reasoning for Complex Visual Question Answering","created":"2025-08-09","cited_by_count":2,"area":"lr"},{"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":"2511.22843","title":"Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2601.19060","title":"Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2409.09362","title":"Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM","created":"2024-09-14","cited_by_count":1,"area":"mllm"},{"id":"2507.04333","title":"Computed Tomography Visual Question Answering with Cross-modal Feature Graphing","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2507.22933","title":"Augmented Vision-Language Models: A Systematic Review","created":"2025-07-24","cited_by_count":1,"area":"mllm"},{"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":"2510.06638","title":"StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering","created":"2025-10-08","cited_by_count":1,"area":"lr"},{"id":"2406.09156","title":"Towards Multilingual Audio-Visual Question Answering","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2501.12697","title":"Combining Knowledge Graph and LLMs for Enhanced Zero-shot Visual Question Answering","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2504.03337","title":"QIRL: Optimized Question-Image Relation Learning for Bias-Robust Visual Question Answering","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2509.09159","title":"A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2602.06050","title":"Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering","created":"2026-01-14","cited_by_count":0,"area":"mllm"},{"id":"2607.21155","title":"CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA","created":"2026-07-23","cited_by_count":0,"area":"mllm"},{"id":"2607.22643","title":"Reason Before You Retrieve: Agentic Planning for Multi-modal RAG","created":"2026-06-24","cited_by_count":0,"area":"rag"},{"id":"2608.23330","title":"IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2610.18161","title":"Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}