{"list":"other","total":64,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"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":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"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":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113},{"id":"2411.00027","title":"Personalization of Large Language Models: A Survey","created":"2024-10-29","cited_by_count":104},{"id":"2404.05970","title":"Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation","created":"2024-04-09","cited_by_count":99},{"id":"2407.11016","title":"LongLaMP: A Benchmark for Personalized Long-form Text Generation","created":"2024-06-27","cited_by_count":97},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"2311.09180","title":"Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers","created":"2023-11-15","cited_by_count":92},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74},{"id":"2405.09798","title":"Many-Shot In-Context Learning in Multimodal Foundation Models","created":"2024-05-16","cited_by_count":67},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64},{"id":"2406.09400","title":"Yo'LLaVA: Your Personalized Language and Vision Assistant","created":"2024-06-13","cited_by_count":62},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51},{"id":"2602.03587","title":"CL-bench: A Benchmark for Context Learning","created":"2026-02-03","cited_by_count":47},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42},{"id":"2402.13349","title":"Aria Everyday Activities Dataset","created":"2024-02-20","cited_by_count":39},{"id":"2403.13164","title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning","created":"2024-03-19","cited_by_count":36},{"id":"2506.00137","title":"LaMP-QA: A Benchmark for Personalized Long-form Question Answering","created":"2025-05-30","cited_by_count":31},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29},{"id":"2507.02001","title":"Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames","created":"2025-07-01","cited_by_count":27},{"id":"2403.12736","title":"Towards Multimodal In-Context Learning for Vision & Language Models","created":"2024-03-19","cited_by_count":25},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24},{"id":"2311.17041","title":"Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties","created":"2023-11-28","cited_by_count":21},{"id":"2601.18157","title":"Agentic Very Long Video Understanding","created":"2026-01-26","cited_by_count":20},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19},{"id":"2510.16282","title":"Instant Personalized Large Language Model Adaptation via Hypernetwork","created":"2025-10-18","cited_by_count":18},{"id":"2411.15556","title":"ReWind: Understanding Long Videos with Instructed Learnable Memory","created":"2024-11-23","cited_by_count":17},{"id":"2412.02186","title":"VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding","created":"2024-12-03","cited_by_count":17},{"id":"2603.24558","title":"LensWalk: Agentic Video Understanding by Planning How You See in Videos","created":"2026-03-25","cited_by_count":17},{"id":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14},{"id":"2503.17069","title":"PVChat: Personalized Video Chat with One-Shot Learning","created":"2025-03-21","cited_by_count":13},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11},{"id":"2308.05822","title":"Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception","created":"2023-08-10","cited_by_count":9},{"id":"2603.20422","title":"PEARL: Personalized Streaming Video Understanding Model","created":"2026-03-20","cited_by_count":9},{"id":"2503.04250","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","created":"2025-03-06","cited_by_count":8},{"id":"2602.08439","title":"Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition","created":"2026-02-09","cited_by_count":8},{"id":"2512.21616","title":"TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant","created":"2025-12-25","cited_by_count":6},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5},{"id":"2506.12258","title":"EgoPrivacy: What Your First-Person Camera Says About You?","created":"2025-06-13","cited_by_count":4},{"id":"2601.15549","title":"VIOLA: Towards Video In-Context Learning with Minimal Annotations","created":"2026-01-22","cited_by_count":2}],"next_cursor":null}