{"total":110,"rows":[{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166,"area":null},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139,"area":null},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109,"area":null},{"id":"2211.08064","title":"Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85,"area":"diffusion"},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78,"area":null},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49,"area":null},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46,"area":null},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45,"area":null},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44,"area":null},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44,"area":"offlinerl"},{"id":"2107.02367","title":"Discrete-Valued Neural Communication","created":"2021-07-06","cited_by_count":39,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36,"area":null},{"id":"2110.15245","title":"From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence","created":"2021-10-28","cited_by_count":35,"area":null},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31,"area":null},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2202.07135","title":"Compositional Scene Representation Learning via Reconstruction: A Survey","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23,"area":null},{"id":"2204.13661","title":"Toward Compositional Generalization in Object-Oriented World Modeling","created":"2022-04-28","cited_by_count":22,"area":"wm"},{"id":"2107.08577","title":"Structured World Belief for Reinforcement Learning in POMDP","created":"2021-07-19","cited_by_count":21,"area":"wm"},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2103.04693","title":"Unsupervised Object-Based Transition Models for 3D Partially Observable Environments","created":"2021-03-08","cited_by_count":20,"area":null},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20,"area":"lr"},{"id":"2410.23254","title":"Keypoint Abstraction using Large Models for Object-Relative Imitation Learning","created":"2024-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2306.05957","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","created":"2023-06-09","cited_by_count":19,"area":null},{"id":"2104.10190","title":"Outcome-Driven Reinforcement Learning via Variational Inference","created":"2021-04-20","cited_by_count":17,"area":null},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","cited_by_count":16,"area":null},{"id":"2307.09205","title":"Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning","created":"2023-07-18","cited_by_count":15,"area":"wm"},{"id":"2603.04553","title":"Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling","created":"2026-03-04","cited_by_count":15,"area":"wm"},{"id":"2202.00368","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2310.12690","title":"Neurosymbolic Grounding for Compositional World Models","created":"2023-10-19","cited_by_count":14,"area":"wm"},{"id":"2404.18926","title":"Point Cloud Models Improve Visual Robustness in Robotic Learners","created":"2024-04-29","cited_by_count":14,"area":null},{"id":"2505.06861","title":"Efficient Robotic Policy Learning via Latent Space Backward Planning","created":"2025-05-11","cited_by_count":14,"area":null},{"id":"2107.08881","title":"Reasoning-Modulated Representations","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2303.01526","title":"Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2304.11470","title":"3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes","created":"2023-04-22","cited_by_count":12,"area":null},{"id":"2508.01345","title":"Predicting Video Slot Attention Queries from Random Slot-Feature Pairs","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2112.03568","title":"Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2205.13271","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2312.11463","title":"Appearance-Based Refinement for Object-Centric Motion Segmentation","created":"2023-12-18","cited_by_count":11,"area":null},{"id":"2204.13022","title":"Binding Actions to Objects in World Models","created":"2022-04-27","cited_by_count":10,"area":"wm"},{"id":"2411.06890","title":"SPARTAN: A Sparse Transformer World Model Attending to What Matters","created":"2024-11-11","cited_by_count":10,"area":"wm"},{"id":"2501.16443","title":"Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"wm"},{"id":"2306.08748","title":"Multi-Object Manipulation via Object-Centric Neural Scattering Functions","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2104.04275","title":"GATSBI: Generative Agent-centric Spatio-temporal Object Interaction","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2303.01869","title":"Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2209.01258","title":"Object-based active inference","created":"2022-09-02","cited_by_count":7,"area":null},{"id":"2303.05501","title":"PDSketch: Integrated Planning Domain Programming and Learning","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2602.02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","created":"2026-02-02","cited_by_count":7,"area":"deeprl"},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2106.09051","title":"Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2110.03473","title":"Unsupervised Image Decomposition with Phase-Correlation Networks","created":"2021-10-07","cited_by_count":6,"area":null},{"id":"2202.05333","title":"Factored World Models for Zero-Shot Generalization in Robotic Manipulation","created":"2022-02-10","cited_by_count":6,"area":"wm"},{"id":"2210.07802","title":"Object-Category Aware Reinforcement Learning","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2303.11373","title":"Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement","created":"2023-03-20","cited_by_count":6,"area":null},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2410.15728","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2102.11448","title":"MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning","created":"2021-02-23","cited_by_count":4,"area":null},{"id":"2401.01922","title":"Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints","created":"2024-01-03","cited_by_count":4,"area":null},{"id":"2404.15109","title":"Compete and Compose: Learning Independent Mechanisms for Modular World Models","created":"2024-04-23","cited_by_count":4,"area":"wm"},{"id":"2501.14174","title":"Dreamweaver: Learning Compositional World Models from Pixels","created":"2025-01-24","cited_by_count":4,"area":"wm"},{"id":"2511.14262","title":"Object-Centric World Models for Causality-Aware Reinforcement Learning","created":"2025-11-18","cited_by_count":4,"area":"wm"},{"id":"2308.11369","title":"Enhancing Interpretable Object Abstraction via Clustering-based Slot Initialization","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2107.11676","title":"The Impact of Negative Sampling on Contrastive Structured World Models","created":"2021-07-24","cited_by_count":2,"area":"wm"},{"id":"2202.08418","title":"Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2206.03591","title":"ObPose: Leveraging Pose for Object-Centric Scene Inference and Generation in 3D","created":"2022-06-07","cited_by_count":2,"area":null},{"id":"2302.03288","title":"Object-Centric Scene Representations using Active Inference","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2310.17649","title":"6-DoF Stability Field via Diffusion Models","created":"2023-10-26","cited_by_count":2,"area":"diffusion"},{"id":"2312.17605","title":"Unified Task and Motion Planning using Object-centric Abstractions of Motion Constraints","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2401.11110","title":"VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE","created":"2024-01-20","cited_by_count":2,"area":null},{"id":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","cited_by_count":2,"area":null},{"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":"2411.17438","title":"Object-centric proto-symbolic behavioural reasoning from pixels","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2206.01370","title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2304.13892","title":"Discovering Object-Centric Generalized Value Functions From Pixels","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2407.03216","title":"Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2503.05092","title":"Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation","created":"2025-03-07","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}