{"total":147,"rows":[{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2305.13311","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","created":"2023-05-22","cited_by_count":103,"area":"diffusion"},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90,"area":"diffusion"},{"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":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54,"area":null},{"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":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49,"area":null},{"id":"2306.06354","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","created":"2023-06-10","cited_by_count":36,"area":"mllm"},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31,"area":null},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2502.10498","title":"The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey","created":"2025-02-14","cited_by_count":29,"area":"wm"},{"id":"2602.11389","title":"Causal-JEPA: Learning World Models through Object-Level Latent Masking","created":"2026-02-11","cited_by_count":29,"area":"wm"},{"id":"2605.06481","title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","created":"2026-05-07","cited_by_count":28,"area":"wm"},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27,"area":"deeprl"},{"id":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2410.10738","title":"DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model","created":"2024-10-14","cited_by_count":25,"area":"wm"},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20,"area":"lr"},{"id":"2302.11850","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2303.02260","title":"Learning to reason over visual objects","created":"2023-03-03","cited_by_count":19,"area":"lr"},{"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":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"id":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17,"area":"wm"},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2301.13197","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","created":"2023-01-30","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":"2503.06170","title":"Object-Centric World Model for Language-Guided Manipulation","created":"2025-03-08","cited_by_count":16,"area":"wm"},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"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":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2502.07600","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2507.23755","title":"Slot Attention with Re-Initialization and Self-Distillation","created":"2025-07-31","cited_by_count":14,"area":"distill"},{"id":"2501.15878","title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","created":"2025-01-27","cited_by_count":13,"area":"diffusion"},{"id":"2506.07865","title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","created":"2025-06-09","cited_by_count":13,"area":null},{"id":"2507.03298","title":"Dyn-O: Building Structured World Models with Object-Centric Representations","created":"2025-07-04","cited_by_count":13,"area":"wm"},{"id":"2503.21747","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","created":"2025-03-27","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":"2312.06721","title":"Understanding Physical Dynamics with Counterfactual World Modeling","created":"2023-12-11","cited_by_count":11,"area":"wm"},{"id":"2403.03458","title":"Slot Abstractors: Toward Scalable Abstract Visual Reasoning","created":"2024-03-06","cited_by_count":11,"area":"lr"},{"id":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11,"area":null},{"id":"2403.04899","title":"Towards Scene Graph Anticipation","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","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":"2410.11251","title":"Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning","created":"2024-10-15","cited_by_count":9,"area":"deeprl"},{"id":"2303.01869","title":"Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2407.15843","title":"CarFormer: Self-Driving with Learned Object-Centric Representations","created":"2024-07-22","cited_by_count":8,"area":"driving"},{"id":"2412.18907","title":"EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation","created":"2024-12-25","cited_by_count":8,"area":null},{"id":"2303.05323","title":"Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","cited_by_count":7,"area":null},{"id":"2401.14718","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","created":"2024-01-26","cited_by_count":7,"area":"wm"},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2601.13304","title":"CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning","created":"2026-01-19","cited_by_count":7,"area":"lr"},{"id":"2602.16229","title":"Factored Latent Action World Models","created":"2026-02-18","cited_by_count":7,"area":"wm"},{"id":"2311.09064","title":"Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models","created":"2023-11-15","cited_by_count":6,"area":"wm"},{"id":"2411.01801","title":"Bootstrapping Top-down Information for Self-modulating Slot Attention","created":"2024-11-04","cited_by_count":6,"area":"lr"},{"id":"2508.05417","title":"Smoothing Slot Attention Iterations and Recurrences","created":"2025-08-07","cited_by_count":6,"area":null},{"id":"2605.31033","title":"SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation","created":"2026-05-29","cited_by_count":6,"area":null},{"id":"2402.05627","title":"Binding Dynamics in Rotating Features","created":"2024-02-08","cited_by_count":5,"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":"2411.02299","title":"Grouped Discrete Representation for Object-Centric Learning","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2411.11467","title":"Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2602.03390","title":"From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2302.10503","title":"Reusable Slotwise Mechanisms","created":"2023-02-21","cited_by_count":4,"area":null},{"id":"2310.10372","title":"Learning Object Permanence from Videos via Latent Imaginations","created":"2023-10-16","cited_by_count":4,"area":null},{"id":"2310.17178","title":"Relational Object-Centric Actor-Critic","created":"2023-10-26","cited_by_count":4,"area":"wm"},{"id":"2311.18296","title":"Perceptual Group Tokenizer: Building Perception with Iterative Grouping","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2501.12477","title":"Slot-BERT: Self-supervised Object Discovery in Surgical Video","created":"2025-01-21","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":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2511.14262","title":"Object-Centric World Models for Causality-Aware Reinforcement Learning","created":"2025-11-18","cited_by_count":4,"area":"wm"},{"id":"2404.18423","title":"OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2405.10598","title":"Top-Down Guidance for Learning Object-Centric Representations","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2506.19408","title":"Is an object-centric representation beneficial for robotic manipulation ?","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2510.02287","title":"MultiModal Action Conditioned Video Generation","created":"2025-10-02","cited_by_count":3,"area":"wm"},{"id":"2510.04978","title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","created":"2025-10-06","cited_by_count":3,"area":"wm"},{"id":"2603.22758","title":"Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2310.08929","title":"Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning","created":"2023-10-13","cited_by_count":2,"area":null},{"id":"2403.07887","title":"Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2407.01726","title":"Grouped Discrete Representation Guides Object-Centric Learning","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2407.04170","title":"Attention Normalization Impacts Cardinality Generalization in Slot Attention","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2412.19847","title":"Symbolic Disentangled Representations for Images","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2505.02074","title":"Learning Local Causal World Models with State Space Models and Attention","created":"2025-05-04","cited_by_count":2,"area":"wm"},{"id":"2506.16129","title":"Neurosymbolic Object-Centric Learning with Distant Supervision","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2602.07564","title":"SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens","created":"2026-02-07","cited_by_count":2,"area":"diffusion"},{"id":"2606.08775","title":"Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks","created":"2026-06-07","cited_by_count":2,"area":"wm"},{"id":"2606.12316","title":"Slots, Transitions, Loops: Learning Composable World Models for ARC","created":"2026-06-10","cited_by_count":2,"area":"wm"},{"id":"2606.12601","title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.13714","title":"TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.15527","title":"Selective Synergistic Learning for Video Object-Centric Learning","created":"2026-06-14","cited_by_count":2,"area":null},{"id":"2606.23436","title":"Rethinking Object-Centric Representations for Video Dynamics Modeling","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2608.15156","title":"Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models","created":"2026-08-15","cited_by_count":2,"area":"wm"},{"id":"2303.09534","title":"InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views","created":"2023-03-16","cited_by_count":1,"area":"wm"},{"id":"2307.07147","title":"Linking vision and motion for self-supervised object-centric perception","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2310.10410","title":"Loci-Segmented: Improving Scene Segmentation Learning","created":"2023-10-16","cited_by_count":1,"area":null}],"next_cursor":"100"}