{"list":"other","total":77,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2107.05720","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","created":"2021-07-12","cited_by_count":286},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2601.04720","title":"Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking","created":"2026-01-08","cited_by_count":230},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213},{"id":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202},{"id":"2401.15884","title":"Corrective Retrieval Augmented Generation","created":"2024-01-29","cited_by_count":197},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2412.16855","title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs","created":"2024-12-22","cited_by_count":170},{"id":"2411.02571","title":"MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs","created":"2024-11-04","cited_by_count":161},{"id":"2412.01720","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","created":"2024-12-02","cited_by_count":106},{"id":"2505.18079","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","created":"2025-05-23","cited_by_count":98},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"2405.13382","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","created":"2024-05-22","cited_by_count":85},{"id":"2412.12075","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","created":"2024-12-16","cited_by_count":85},{"id":"2404.07220","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","created":"2024-03-22","cited_by_count":84},{"id":"2412.16117","title":"PruneVid: Visual Token Pruning for Efficient Video Large Language Models","created":"2024-12-20","cited_by_count":67},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64},{"id":"2503.10200","title":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","created":"2025-03-13","cited_by_count":58},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55},{"id":"2512.02425","title":"WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning","created":"2025-12-02","cited_by_count":53},{"id":"2311.07838","title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","created":"2023-11-14","cited_by_count":52},{"id":"1708.00247","title":"Query expansion techniques for information retrieval: A survey","created":"2017-08-01","cited_by_count":44},{"id":"2402.03367","title":"RAG-Fusion: a New Take on Retrieval-Augmented Generation","created":"2024-01-31","cited_by_count":42},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37},{"id":"2401.16702","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","created":"2024-01-30","cited_by_count":34},{"id":"2304.05088","title":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","created":"2023-04-11","cited_by_count":32},{"id":"2412.09530","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","created":"2024-12-12","cited_by_count":32},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29},{"id":"2601.18157","title":"Agentic Very Long Video Understanding","created":"2026-01-26","cited_by_count":20},{"id":"2401.06311","title":"Exploring the Best Practices of Query Expansion with Large Language Models","created":"2024-01-12","cited_by_count":17},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17},{"id":"2401.04055","title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval","created":"2024-01-08","cited_by_count":16},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","cited_by_count":16},{"id":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15},{"id":"2510.05038","title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","created":"2025-10-06","cited_by_count":12},{"id":"2408.17072","title":"MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models","created":"2024-08-30","cited_by_count":9},{"id":"2603.24373","title":"PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks","created":"2026-03-25","cited_by_count":9},{"id":"2504.04550","title":"Advancing Egocentric Video Question Answering with Multimodal Large Language Models","created":"2025-04-06","cited_by_count":8},{"id":"2509.12765","title":"InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering","created":"2025-09-16","cited_by_count":8},{"id":"2509.24621","title":"FreeRet: MLLMs as Training-Free Retrievers","created":"2025-09-29","cited_by_count":8},{"id":"2603.05484","title":"Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline","created":"2026-03-05","cited_by_count":8},{"id":"2503.23013","title":"DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation","created":"2025-03-29","cited_by_count":7},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5},{"id":"2508.05512","title":"RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback","created":"2025-08-07","cited_by_count":5},{"id":"2602.23709","title":"EgoGraph: Temporal Knowledge Graph for Egocentric Video Understanding","created":"2026-02-27","cited_by_count":3},{"id":"2603.29616","title":"Video-Oasis: Rethinking Evaluation of Video Understanding","created":"2026-03-31","cited_by_count":3},{"id":"2601.22508","title":"CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content","created":"2026-01-30","cited_by_count":2},{"id":"2604.04372","title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","created":"2026-04-06","cited_by_count":2},{"id":"2601.06097","title":"Semantic Event Graphs for Long-Form Video Question Answering","created":"2026-01-02","cited_by_count":1}],"next_cursor":null}