{"total":94,"rows":[{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"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":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"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":"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":"2501.05874","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","created":"2025-01-10","cited_by_count":57,"area":"rag"},{"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":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42,"area":"mllm"},{"id":"2412.10704","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":41,"area":"rag"},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40,"area":null},{"id":"2410.21943","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","created":"2024-10-29","cited_by_count":31,"area":"rag"},{"id":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23,"area":null},{"id":"2510.01149","title":"ModernVBERT: Towards Smaller Visual Document Retrievers","created":"2025-10-01","cited_by_count":21,"area":"rag"},{"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":"2510.14605","title":"Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering","created":"2025-10-16","cited_by_count":17,"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":"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":"2311.11598","title":"Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions","created":"2023-11-20","cited_by_count":14,"area":"lr"},{"id":"2405.14839","title":"A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis","created":"2024-05-23","cited_by_count":14,"area":null},{"id":"2301.11507","title":"Semi-Parametric Video-Grounded Text Generation","created":"2023-01-27","cited_by_count":13,"area":null},{"id":"2412.21023","title":"EdgeRAG: Online-Indexed RAG for Edge Devices","created":"2024-12-30","cited_by_count":13,"area":"rag"},{"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":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2603.00873","title":"MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains","created":"2026-03-01","cited_by_count":12,"area":"lr"},{"id":"2305.04530","title":"A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues","created":"2023-05-08","cited_by_count":11,"area":"lr"},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2505.07879","title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval","created":"2025-05-10","cited_by_count":10,"area":"rag"},{"id":"2509.18436","title":"Memory-QA: Answering Recall Questions Based on Multimodal Memories","created":"2025-09-22","cited_by_count":10,"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":"2407.02233","title":"Synthetic Multimodal Question Generation","created":"2024-07-02","cited_by_count":8,"area":"rag"},{"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":"2504.02132","title":"One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image","created":"2025-04-02","cited_by_count":8,"area":"rag"},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2312.06141","title":"Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applications","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2502.18023","title":"Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2602.22683","title":"SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses","created":"2026-02-26","cited_by_count":6,"area":"mllm"},{"id":"2401.02993","title":"ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion","created":"2024-01-04","cited_by_count":5,"area":null},{"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":"2505.13957","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"rag"},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2303.10699","title":"FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering","created":"2023-03-19","cited_by_count":4,"area":null},{"id":"2403.11317","title":"Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches","created":"2024-03-17","cited_by_count":4,"area":null},{"id":"2410.11321","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","created":"2024-10-15","cited_by_count":4,"area":"rag"},{"id":"2501.15470","title":"CogPlanner: Unveiling the Potential of Agentic Multimodal Retrieval Augmented Generation with Planning","created":"2025-01-26","cited_by_count":4,"area":"mllm"},{"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":"2412.10151","title":"VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generation","created":"2024-12-13","cited_by_count":3,"area":"mllm"},{"id":"2503.09081","title":"Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2511.15435","title":"HV-Attack: Hierarchical Visual Attack for Multimodal Retrieval Augmented Generation","created":"2025-11-19","cited_by_count":3,"area":"mllm"},{"id":"2605.12497","title":"From Web to Pixels: Bringing Agentic Search into Visual Perception","created":"2026-05-12","cited_by_count":3,"area":"agents"},{"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":"2306.17675","title":"Multimodal Prompt Retrieval for Generative Visual Question Answering","created":"2023-06-30","cited_by_count":2,"area":"mllm"},{"id":"2406.00872","title":"OLIVE: Object Level In-Context Visual Embeddings","created":"2024-06-02","cited_by_count":2,"area":"lr"},{"id":"2502.13836","title":"Quantifying Memorization and Parametric Response Rates in Retrieval-Augmented Vision-Language Models","created":"2025-02-19","cited_by_count":2,"area":"mllm"},{"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":"2507.23217","title":"Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented Generation","created":"2025-07-31","cited_by_count":2,"area":"mllm"},{"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":"2602.23952","title":"CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering","created":"2026-02-27","cited_by_count":2,"area":null},{"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":"2405.11145","title":"Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2506.10030","title":"Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment","created":"2025-06-10","cited_by_count":1,"area":"rag"},{"id":"2507.22933","title":"Augmented Vision-Language Models: A Systematic Review","created":"2025-07-24","cited_by_count":1,"area":"mllm"},{"id":"2508.08816","title":"Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2509.02123","title":"CMRAG: Co-modality-based visual document retrieval and question answering","created":"2025-09-02","cited_by_count":1,"area":"rag"},{"id":"2512.05959","title":"M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG","created":"2025-12-05","cited_by_count":1,"area":"mllm"},{"id":"2601.11632","title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","created":"2026-01-14","cited_by_count":1,"area":"mllm"},{"id":"2602.00344","title":"When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2607.04683","title":"Failing to See or Failing to Know? Attributing Errors in Vision-Language Models","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2608.21431","title":"Boosting Knowledge-based Visual Question Answering with Structured Context Reasoning","created":"2026-08-17","cited_by_count":1,"area":"lr"},{"id":"2307.14750","title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","created":"2023-07-27","cited_by_count":0,"area":"rag"},{"id":"2312.02188","title":"Video Summarization: Towards Entity-Aware Captions","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2403.10798","title":"Object Retrieval for Visual Question Answering with Outside Knowledge","created":"2024-03-16","cited_by_count":0,"area":"rag"},{"id":"2507.00068","title":"MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2508.19724","title":"NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks","created":"2025-08-27","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":"2604.05268","title":"Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking","created":"2026-04-07","cited_by_count":0,"area":"rag"},{"id":"2604.22678","title":"BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering","created":"2026-04-24","cited_by_count":0,"area":"rag"},{"id":"2605.07273","title":"From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG","created":"2026-05-08","cited_by_count":0,"area":"rag"},{"id":"2606.03354","title":"ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation","created":"2026-06-02","cited_by_count":0,"area":"rag"},{"id":"2607.07383","title":"MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"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":"2607.25422","title":"Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.01147","title":"UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.02907","title":"Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.21796","title":"SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.23176","title":"Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.13267","title":"Structure-Token Evidence-Anchored Reasoning for Scientific Chart Understanding","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.13268","title":"Capability-Routed Visual Retrieval and Evidence Threading for Long-Context Document Question Answering","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.12517","title":"TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}