{"list":"other","total":85,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"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":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1803.01422","title":"DAGs with NO TEARS: Continuous Optimization for Structure Learning","created":"2018-03-04","cited_by_count":752},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2108.03272","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","created":"2021-08-06","cited_by_count":194},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2006.10833","title":"Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data","created":"2020-06-18","cited_by_count":100},{"id":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84},{"id":"2107.10483","title":"Efficient Neural Causal Discovery without Acyclicity Constraints","created":"2021-07-22","cited_by_count":82},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","cited_by_count":68},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"1912.11032","title":"Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning","created":"2019-12-23","cited_by_count":55},{"id":"2010.03110","title":"Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning","created":"2020-10-07","cited_by_count":53},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"2011.14381","title":"Self-supervised Visual Reinforcement Learning with Object-centric Representations","created":"2020-11-29","cited_by_count":44},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44},{"id":"2402.13181","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","created":"2024-02-20","cited_by_count":44},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44},{"id":"1403.3741","title":"Near-optimal Reinforcement Learning in Factored MDPs","created":"2014-03-15","cited_by_count":41},{"id":"2312.12444","title":"What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?","created":"2023-11-03","cited_by_count":39},{"id":"2004.08763","title":"Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization","created":"2020-04-19","cited_by_count":32},{"id":"2410.21869","title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","created":"2024-10-29","cited_by_count":31},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27},{"id":"2210.06964","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","created":"2022-10-13","cited_by_count":24},{"id":"2307.03567","title":"SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks","created":"2023-07-07","cited_by_count":24},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23},{"id":"2204.13661","title":"Toward Compositional Generalization in Object-Oriented World Modeling","created":"2022-04-28","cited_by_count":22},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22},{"id":"2201.13388","title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","created":"2022-01-31","cited_by_count":19},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16},{"id":"2312.03009","title":"I-PHYRE: Interactive Physical Reasoning","created":"2023-12-04","cited_by_count":15},{"id":"2504.15369","title":"Solving New Tasks by Adapting Internet Video Knowledge","created":"2025-04-21","cited_by_count":13},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12},{"id":"2406.03234","title":"Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning","created":"2024-06-05","cited_by_count":11},{"id":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9},{"id":"2104.04275","title":"GATSBI: Generative Agent-centric Spatio-temporal Object Interaction","created":"2021-04-09","cited_by_count":8},{"id":"2310.08702","title":"ELDEN: Exploration via Local Dependencies","created":"2023-10-12","cited_by_count":8},{"id":"2507.12496","title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","created":"2025-07-15","cited_by_count":8},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6},{"id":"2505.03172","title":"Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning","created":"2025-05-06","cited_by_count":6},{"id":"2502.10077","title":"Towards Empowerment Gain through Causal Structure Learning in Model-Based RL","created":"2025-02-14","cited_by_count":5},{"id":"2510.12403","title":"Robot Learning: A Tutorial","created":"2025-10-14","cited_by_count":5},{"id":"2501.14174","title":"Dreamweaver: Learning Compositional World Models from Pixels","created":"2025-01-24","cited_by_count":4},{"id":"2502.10097","title":"Causal Information Prioritization for Efficient Reinforcement Learning","created":"2025-02-14","cited_by_count":4},{"id":"2311.09350","title":"Generalizable Imitation Learning Through Pre-Trained Representations","created":"2023-11-15","cited_by_count":3},{"id":"2405.12615","title":"Learning Causal Dynamics Models in Object-Oriented Environments","created":"2024-05-21","cited_by_count":3},{"id":"2407.10967","title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning","created":"2024-07-15","cited_by_count":3}],"next_cursor":null}