{"total":101,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081,"area":"wm"},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261,"area":"wm"},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191,"area":"wm"},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108,"area":null},{"id":"2402.14083","title":"Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping","created":"2024-02-21","cited_by_count":90,"area":"lr"},{"id":"2401.09985","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","created":"2024-01-18","cited_by_count":89,"area":"wm"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73,"area":"diffusion"},{"id":"2407.09450","title":"Human-inspired Episodic Memory for Infinite Context LLMs","created":"2024-07-12","cited_by_count":62,"area":null},{"id":"2604.03208","title":"Hierarchical Planning with Latent World Models","created":"2026-04-03","cited_by_count":43,"area":"wm"},{"id":"2508.17600","title":"GWM: Towards Scalable Gaussian World Models for Robotic Manipulation","created":"2025-08-25","cited_by_count":39,"area":"wm"},{"id":"2502.07202","title":"Monte Carlo Tree Diffusion for System 2 Planning","created":"2025-02-11","cited_by_count":33,"area":"lr"},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"area":null},{"id":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27,"area":"wm"},{"id":"2410.03132","title":"Autoregressive Action Sequence Learning for Robotic Manipulation","created":"2024-10-04","cited_by_count":27,"area":null},{"id":"2312.17227","title":"Gradient-based Planning with World Models","created":"2023-12-28","cited_by_count":19,"area":"wm"},{"id":"2405.14853","title":"Privileged Sensing Scaffolds Reinforcement Learning","created":"2024-05-23","cited_by_count":19,"area":null},{"id":"2407.08464","title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","created":"2024-07-11","cited_by_count":17,"area":"deeprl"},{"id":"2512.16811","title":"GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation","created":"2025-12-18","cited_by_count":17,"area":"vla"},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2306.00867","title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","created":"2023-06-01","cited_by_count":14,"area":"offlinerl"},{"id":"2410.03618","title":"Open-World Reinforcement Learning over Long Short-Term Imagination","created":"2024-10-04","cited_by_count":13,"area":"wm"},{"id":"2406.00483","title":"Exploring the limits of Hierarchical World Models in Reinforcement Learning","created":"2024-06-01","cited_by_count":11,"area":"wm"},{"id":"2505.14975","title":"Flattening Hierarchies with Policy Bootstrapping","created":"2025-05-20","cited_by_count":11,"area":"synth"},{"id":"2506.14135","title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","created":"2025-06-17","cited_by_count":11,"area":"wm"},{"id":"2506.19842","title":"ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model","created":"2025-06-24","cited_by_count":11,"area":"wm"},{"id":"2403.09976","title":"AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors","created":"2024-03-15","cited_by_count":10,"area":"wm"},{"id":"2602.10104","title":"Olaf-World: Orienting Latent Actions for Video World Modeling","created":"2026-02-10","cited_by_count":10,"area":"wm"},{"id":"2302.05342","title":"Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL","created":"2023-02-10","cited_by_count":9,"area":null},{"id":"2503.01584","title":"SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models","created":"2025-03-03","cited_by_count":9,"area":"wm"},{"id":"2507.06710","title":"Spatial-Temporal Aware Visuomotor Diffusion Policy Learning","created":"2025-07-09","cited_by_count":9,"area":"diffusion"},{"id":"2310.05167","title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","created":"2023-10-08","cited_by_count":8,"area":"wm"},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"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,"area":"wm"},{"id":"2304.00046","title":"Accelerating exploration and representation learning with offline pre-training","created":"2023-03-31","cited_by_count":7,"area":null},{"id":"2305.15260","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","created":"2023-05-24","cited_by_count":7,"area":"wm"},{"id":"2509.09737","title":"World Modeling with Probabilistic Structure Integration","created":"2025-09-10","cited_by_count":7,"area":"wm"},{"id":"2602.19634","title":"Compositional Planning with Jumpy World Models","created":"2026-02-23","cited_by_count":7,"area":"wm"},{"id":"2402.18866","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","created":"2024-02-29","cited_by_count":6,"area":"deeprl"},{"id":"2406.06793","title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","created":"2024-06-10","cited_by_count":6,"area":"offlinerl"},{"id":"2503.08751","title":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","created":"2025-03-11","cited_by_count":6,"area":"wm"},{"id":"2410.18800","title":"PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds","created":"2024-10-24","cited_by_count":5,"area":"deeprl"},{"id":"2607.06401","title":"A Definition and Roadmap for World Models","created":"2026-07-07","cited_by_count":5,"area":"wm"},{"id":"2310.00229","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2405.03865","title":"Information-driven Affordance Discovery for Efficient Robotic Manipulation","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2406.15850","title":"Learning Abstract World Model for Value-preserving Planning with Options","created":"2024-06-22","cited_by_count":4,"area":"wm"},{"id":"2406.18033","title":"Boosting Soft Q-Learning by Bounding","created":"2024-06-26","cited_by_count":4,"area":"deeprl"},{"id":"2410.14616","title":"Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environments","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2410.17551","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2410.21616","title":"Identifying Selections for Unsupervised Subtask Discovery","created":"2024-10-28","cited_by_count":4,"area":"offlinerl"},{"id":"2411.00588","title":"$\\alpha$-TCVAE: On the relationship between Disentanglement and Diversity","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2501.09905","title":"SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor Learning","created":"2025-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2207.08192","title":"BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environment","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2301.10067","title":"Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review","created":"2023-01-24","cited_by_count":3,"area":"wm"},{"id":"2311.16996","title":"Goal-conditioned Offline Planning from Curious Exploration","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2404.04929","title":"RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models","created":"2024-04-07","cited_by_count":3,"area":"lr"},{"id":"2606.00133","title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2210.06168","title":"The Role of Exploration for Task Transfer in Reinforcement Learning","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2312.05044","title":"Backward Learning for Goal-Conditioned Policies","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2406.17168","title":"Reinforcement Learning via Auxiliary Task Distillation","created":"2024-06-24","cited_by_count":2,"area":"deeprl"},{"id":"2408.11816","title":"Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction","created":"2024-08-21","cited_by_count":2,"area":"wm"},{"id":"2503.20102","title":"Extendable Planning via Multiscale Diffusion","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2510.00600","title":"Hybrid Training for Vision-Language-Action Models","created":"2025-10-01","cited_by_count":2,"area":"vla"},{"id":"2604.10333","title":"Zero-shot World Models Are Developmentally Efficient Learners","created":"2026-04-11","cited_by_count":2,"area":"wm"},{"id":"2605.04525","title":"HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks","created":"2026-05-06","cited_by_count":2,"area":"diffusion"},{"id":"2605.30484","title":"ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation","created":"2026-05-28","cited_by_count":2,"area":"vla"},{"id":"2310.01569","title":"Iterative Option Discovery for Planning, by Planning","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2402.14244","title":"MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint","created":"2024-02-22","cited_by_count":1,"area":"alignment"},{"id":"2403.16824","title":"On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2404.00651","title":"Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration","created":"2024-03-31","cited_by_count":1,"area":"deeprl"},{"id":"2410.07096","title":"Rejecting Hallucinated State Targets during Planning","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2502.19920","title":"Pokemon Red via Reinforcement Learning","created":"2025-02-27","cited_by_count":1,"area":"deeprl"},{"id":"2505.06482","title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach","created":"2025-05-10","cited_by_count":1,"area":"offlinerl"},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2602.02799","title":"Joint Learning of Hierarchical Neural Options and Abstract World Model","created":"2026-02-02","cited_by_count":1,"area":"wm"},{"id":"2603.22273","title":"Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration","created":"2026-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2604.15679","title":"Hierarchical Active Inference using Successor Representations","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.09364","title":"MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","created":"2026-05-10","cited_by_count":1,"area":"deeprl"},{"id":"2607.02087","title":"SUNTA: Hierarchical Video Prediction with Surprise-based Chunking","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2609.36473","title":"Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2310.09997","title":"Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels","created":"2023-10-16","cited_by_count":0,"area":"wm"},{"id":"2312.02522","title":"MASP: Scalable GNN-based Planning for Multi-Agent Navigation","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2407.00264","title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling","created":"2024-06-28","cited_by_count":0,"area":"deeprl"},{"id":"2407.19142","title":"On the benefits of pixel-based hierarchical policies for task generalization","created":"2024-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2410.21059","title":"Predictive Reachability for Embodiment Selection in Mobile Manipulation Behaviors","created":"2024-10-28","cited_by_count":0,"area":"wm"},{"id":"2411.13607","title":"VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2502.01956","title":"DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents","created":"2025-02-04","cited_by_count":0,"area":"deeprl"},{"id":"2503.09867","title":"Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.21410","title":"MRS: Multi-Resolution Skills for HRL Agents","created":"2025-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2605.17058","title":"Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning","created":"2026-05-16","cited_by_count":0,"area":"wm"},{"id":"2605.26371","title":"Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.15301","title":"Discovering Lattice Reduction Strategies via Self-Play","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.07763","title":"Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models","created":"2026-07-08","cited_by_count":0,"area":"wm"},{"id":"2607.15898","title":"Orbis 2: A Hierarchical World Model for Driving","created":"2026-07-17","cited_by_count":0,"area":"wm"},{"id":"2610.04988","title":"How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models","created":"2026-10-04","cited_by_count":0,"area":"wm"},{"id":"2610.05446","title":"Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.06805","title":"H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning","created":"2026-10-05","cited_by_count":0,"area":"wm"}],"next_cursor":"100"}