{"total":100,"rows":[{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182,"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":"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":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88,"area":null},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85,"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":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"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":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"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":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"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":"2205.13817","title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models","created":"2022-05-27","cited_by_count":53,"area":"wm"},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50,"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":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2107.02367","title":"Discrete-Valued Neural Communication","created":"2021-07-06","cited_by_count":39,"area":null},{"id":"2206.07681","title":"Learning to Accelerate Partial Differential Equations via Latent Global Evolution","created":"2022-06-15","cited_by_count":39,"area":null},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38,"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":"2108.01316","title":"RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting","created":"2021-08-03","cited_by_count":36,"area":null},{"id":"2202.13519","title":"PartAfford: Part-level Affordance Discovery from 3D Objects","created":"2022-02-28","cited_by_count":36,"area":null},{"id":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31,"area":"lr"},{"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":"2106.11083","title":"Conditional Neural Relational Inference for Interacting Systems","created":"2021-06-21","cited_by_count":28,"area":null},{"id":"2206.13114","title":"Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoning","created":"2022-06-27","cited_by_count":28,"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":"2110.15497","title":"Unsupervised Foreground Extraction via Deep Region Competition","created":"2021-10-29","cited_by_count":26,"area":"moe"},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24,"area":null},{"id":"2311.02007","title":"Towards Unsupervised Object Detection From LiDAR Point Clouds","created":"2023-11-03","cited_by_count":23,"area":null},{"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":"2310.19054","title":"Object-centric architectures enable efficient causal representation learning","created":"2023-10-29","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":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","cited_by_count":16,"area":null},{"id":"2305.15001","title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2310.07015","title":"Neural Relational Inference with Fast Modular Meta-learning","created":"2023-10-10","cited_by_count":16,"area":null},{"id":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2107.08881","title":"Reasoning-Modulated Representations","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2204.08479","title":"Inductive Biases for Object-Centric Representations in the Presence of Complex Textures","created":"2022-04-18","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":"2106.05897","title":"Unsupervised Co-part Segmentation through Assembly","created":"2021-06-10","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":"2305.16543","title":"Revisiting Structured Variational Autoencoders","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2311.04640","title":"Object-Centric Learning with Slot Mixture Module","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2101.09486","title":"Neural Relational Inference with Efficient Message Passing Mechanisms","created":"2021-01-23","cited_by_count":10,"area":null},{"id":"2102.13419","title":"Iterative SE(3)-Transformers","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"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":"2203.11194","title":"Test-time Adaptation with Slot-Centric Models","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2410.19923","title":"Language Agents Meet Causality -- Bridging LLMs and Causal World Models","created":"2024-10-25","cited_by_count":9,"area":"wm"},{"id":"2104.04275","title":"GATSBI: Generative Agent-centric Spatio-temporal Object Interaction","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2102.11905","title":"Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2103.10611","title":"Knowledge-Guided Object Discovery with Acquired Deep Impressions","created":"2021-03-19","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":"2102.02100","title":"Object and Relation Centric Representations for Push Effect Prediction","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2206.03010","title":"MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learning","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2310.14466","title":"Inferring Relational Potentials in Interacting Systems","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2402.03326","title":"Slot Structured World Models","created":"2024-01-08","cited_by_count":5,"area":"wm"},{"id":"2112.01603","title":"Neurosymbolic Systems of Perception & Cognition: The Role of Attention","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2302.10503","title":"Reusable Slotwise Mechanisms","created":"2023-02-21","cited_by_count":4,"area":null},{"id":"2303.14889","title":"Model-Based Reinforcement Learning with Isolated Imaginations","created":"2023-03-27","cited_by_count":4,"area":"wm"},{"id":"2401.01922","title":"Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints","created":"2024-01-03","cited_by_count":4,"area":null},{"id":"2401.10148","title":"Explicitly Disentangled Representations in Object-Centric Learning","created":"2024-01-18","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":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2501.14174","title":"Dreamweaver: Learning Compositional World Models from Pixels","created":"2025-01-24","cited_by_count":4,"area":"wm"},{"id":"2101.04041","title":"Evaluating Disentanglement of Structured Representations","created":"2021-01-11","cited_by_count":3,"area":null},{"id":"2211.06027","title":"Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2603.14483","title":"Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2102.01223","title":"Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention","created":"2021-02-01","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":"2311.07534","title":"Unsupervised Musical Object Discovery from Audio","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2106.04776","title":"Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2111.05514","title":"Discovering Latent Representations of Relations for Interacting Systems","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2302.05448","title":"The Construction of Reality in an AI: A Review","created":"2023-02-03","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":"2105.08111","title":"Livewired Neural Networks: Making Neurons That Fire Together Wire Together","created":"2021-05-17","cited_by_count":0,"area":null},{"id":"2106.16060","title":"Leveraging Hidden Structure in Self-Supervised Learning","created":"2021-06-30","cited_by_count":0,"area":null},{"id":"2202.06036","title":"Neural NID Rules","created":"2022-02-12","cited_by_count":0,"area":null},{"id":"2310.18807","title":"OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning","created":"2023-10-28","cited_by_count":0,"area":"lr"},{"id":"2311.02123","title":"RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2506.07806","title":"Identifiable Object Representations under Spatial Ambiguities","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2508.16836","title":"Physics-Inspired Spatial Temporal Graph Neural Networks for Predicting Industrial Chain Resilience","created":"2025-08-22","cited_by_count":0,"area":null}],"next_cursor":null}