{"total":57,"rows":[{"id":"2503.10200","title":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","created":"2025-03-13","cited_by_count":58,"area":"agents"},{"id":"2512.02425","title":"WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning","created":"2025-12-02","cited_by_count":53,"area":"lr"},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50,"area":"agents"},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2508.21475","title":"MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents","created":"2025-08-29","cited_by_count":38,"area":"lr"},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","cited_by_count":32,"area":"rag"},{"id":"2512.12360","title":"VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding","created":"2025-12-13","cited_by_count":25,"area":"lr"},{"id":"2504.20734","title":"UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities","created":"2025-04-29","cited_by_count":20,"area":"rag"},{"id":"2506.01274","title":"ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding","created":"2025-06-02","cited_by_count":16,"area":"mllm"},{"id":"2510.10518","title":"VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning","created":"2025-10-12","cited_by_count":12,"area":"lr"},{"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":"2601.13719","title":"Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search","created":"2026-01-20","cited_by_count":8,"area":"mllm"},{"id":"2505.03173","title":"RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph","created":"2025-05-06","cited_by_count":7,"area":"mllm"},{"id":"2506.07600","title":"SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding","created":"2025-06-09","cited_by_count":7,"area":"rag"},{"id":"2606.07512","title":"MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism","created":"2026-06-05","cited_by_count":7,"area":"lr"},{"id":"2504.04988","title":"Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model","created":"2025-04-07","cited_by_count":6,"area":"rag"},{"id":"2510.07915","title":"MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding","created":"2025-10-09","cited_by_count":6,"area":"inference"},{"id":"2511.19524","title":"VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning","created":"2025-11-24","cited_by_count":6,"area":"mllm"},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6,"area":"mllm"},{"id":"2602.12735","title":"VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph","created":"2026-02-13","cited_by_count":5,"area":"rag"},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2511.12027","title":"GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory","created":"2025-11-15","cited_by_count":4,"area":"mllm"},{"id":"2602.05275","title":"Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs","created":"2026-02-05","cited_by_count":3,"area":"mllm"},{"id":"2505.13557","title":"AMAQA: A Metadata-based QA Dataset for RAG Systems","created":"2025-05-19","cited_by_count":2,"area":"rag"},{"id":"2506.21556","title":"VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph Dataset for Retrieval-Augmented Generation","created":"2025-06-11","cited_by_count":2,"area":"lr"},{"id":"2509.21559","title":"X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2510.15543","title":"MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2603.22285","title":"VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2608.07663","title":"Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding","created":"2026-08-07","cited_by_count":2,"area":"mllm"},{"id":"2508.03967","title":"RAVID: Retrieval-Augmented Visual Detection: A Knowledge-Driven Approach for AI-Generated Image Identification","created":"2025-08-05","cited_by_count":1,"area":"rag"},{"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":"2510.24870","title":"Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation","created":"2025-10-28","cited_by_count":1,"area":"rag"},{"id":"2603.10765","title":"RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems","created":"2026-03-11","cited_by_count":1,"area":"rag"},{"id":"2603.22872","title":"ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.19075","title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.09109","title":"Driving Video Retrieval for Complex Queries with Structured Grounding","created":"2026-06-08","cited_by_count":1,"area":"driving"},{"id":"2606.13141","title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2609.00551","title":"EM^2Mem: Event-Centric Multimodal Memory for Large Language Models","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2512.17108","title":"Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2512.20136","title":"M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation","created":"2025-12-23","cited_by_count":0,"area":"mllm"},{"id":"2603.27259","title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.23145","title":"UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks","created":"2026-04-25","cited_by_count":0,"area":"lr"},{"id":"2605.29250","title":"OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.06532","title":"GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.21734","title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","created":"2026-06-19","cited_by_count":0,"area":"lr"},{"id":"2607.24760","title":"CHaystack: Benchmarking Chinese Document Retrieval and VQA","created":"2026-05-30","cited_by_count":0,"area":"rag"},{"id":"2608.08075","title":"Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.23011","title":"Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2608.28699","title":"Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.14066","title":"GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning","created":"2026-09-12","cited_by_count":0,"area":"lr"},{"id":"2609.19664","title":"VideoResearcher: Self-Improving Tool Design for Long-Video Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.01884","title":"Memory-Guided B-Roll Generation from User Video Collections","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01936","title":"Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02451","title":"A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.05526","title":"Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}