{"list":"other","total":56,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"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":"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":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"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":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"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":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186},{"id":"2410.07166","title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making","created":"2024-10-09","cited_by_count":144},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2506.03569","title":"MiMo-VL Technical Report","created":"2025-06-04","cited_by_count":115},{"id":"2508.11737","title":"Ovis2.5 Technical Report","created":"2025-08-15","cited_by_count":108},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"2509.01563","title":"Kwai Keye-VL 1.5 Technical Report","created":"2025-09-01","cited_by_count":73},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"2501.00584","title":"Online Video Understanding: OVBench and VideoChat-Online","created":"2024-12-31","cited_by_count":61},{"id":"2311.15596","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","created":"2023-11-27","cited_by_count":60},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44},{"id":"2503.06157","title":"UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces","created":"2025-03-08","cited_by_count":36},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32},{"id":"2412.08614","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","created":"2024-12-11","cited_by_count":31},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26},{"id":"2305.12140","title":"Movie101: A New Movie Understanding Benchmark","created":"2023-05-20","cited_by_count":25},{"id":"2506.05287","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","created":"2025-06-05","cited_by_count":21},{"id":"2508.10729","title":"EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering","created":"2025-08-14","cited_by_count":21},{"id":"2501.05031","title":"ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark","created":"2025-01-09","cited_by_count":19},{"id":"2512.14014","title":"MobileWorldBench: Towards Semantic World Modeling For Mobile Agents","created":"2025-12-16","cited_by_count":18},{"id":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2511.20937","title":"ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction","created":"2025-11-26","cited_by_count":15},{"id":"2510.23981","title":"TeleEgo: Benchmarking Egocentric AI Assistants in the Wild","created":"2025-10-28","cited_by_count":11},{"id":"2512.02895","title":"MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm","created":"2025-12-02","cited_by_count":9},{"id":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","cited_by_count":8},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7},{"id":"2602.01983","title":"Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning","created":"2026-02-02","cited_by_count":7},{"id":"2512.20735","title":"VL4Gaze: Unleashing Vision-Language Models for Gaze Following","created":"2025-12-23","cited_by_count":3},{"id":"2601.06750","title":"Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models","created":"2026-01-11","cited_by_count":1}],"next_cursor":null}