{"list":"other","total":61,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79},{"id":"2505.01425","title":"GENMO: A GENeralist Model for Human MOtion","created":"2025-05-02","cited_by_count":49},{"id":"2301.13280","title":"WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics","created":"2023-01-30","cited_by_count":47},{"id":"2406.10819","title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding","created":"2024-06-16","cited_by_count":43},{"id":"2406.10227","title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos","created":"2024-06-14","cited_by_count":35},{"id":"2501.16150","title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","created":"2025-01-27","cited_by_count":34},{"id":"2505.02024","title":"From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent","created":"2025-05-04","cited_by_count":33},{"id":"2012.06738","title":"Learning Multi-Arm Manipulation Through Collaborative Teleoperation","created":"2020-12-12","cited_by_count":32},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29},{"id":"2504.16925","title":"Latent Diffusion Planning for Imitation Learning","created":"2025-04-23","cited_by_count":26},{"id":"2209.10447","title":"Hierarchical Decision Transformer","created":"2022-09-21","cited_by_count":16},{"id":"2008.04431","title":"Measures of Complexity for Large Scale Image Datasets","created":"2020-08-10","cited_by_count":14},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14}],"next_cursor":null}