{"total":43,"rows":[{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"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":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"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":"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":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"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":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19,"area":null},{"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":"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":"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":"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":"2209.00853","title":"TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification","created":"2022-09-02","cited_by_count":13,"area":null},{"id":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2505.00209","title":"Direct Motion Models for Assessing Generated Videos","created":"2025-04-30","cited_by_count":10,"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":"2303.05323","title":"Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"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":"2410.15728","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","created":"2024-10-21","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":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2209.09115","title":"Compositional Law Parsing with Latent Random Functions","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2301.08951","title":"Time-Conditioned Generative Modeling of Object-Centric Representations for Video Decomposition and Prediction","created":"2023-01-21","cited_by_count":3,"area":null},{"id":"2404.18423","title":"OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2106.13798","title":"Conjugate Energy-Based Models","created":"2021-06-25","cited_by_count":2,"area":null},{"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":"2302.03288","title":"Object-Centric Scene Representations using Active Inference","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","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":"2211.11500","title":"Compositional Scene Modeling with Global Object-Centric Representations","created":"2022-11-21","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":"2501.19182","title":"A Compressive-Expressive Communication Framework for Compositional Representations","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2602.07544","title":"MUFASA: A Multi-Layer Framework for Slot Attention","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2605.03650","title":"Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2407.09537","title":"ViPro: Enabling and Controlling Video Prediction for Complex Dynamical Scenarios using Procedural Knowledge","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2507.20855","title":"Compositional Video Synthesis by Temporal Object-Centric Learning","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2610.01201","title":"iSEE: Object Permanence Through Self-Supervision","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}