{"total":42,"rows":[{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261,"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":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"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":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93,"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":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"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":"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":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"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":"2202.06481","title":"A Survey on Machine Learning Approaches for Modelling Intuitive Physics","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2306.06997","title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","created":"2023-06-12","cited_by_count":20,"area":null},{"id":"2305.11772","title":"Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes","created":"2023-05-19","cited_by_count":13,"area":null},{"id":"2107.00683","title":"Active Learning of Abstract Plan Feasibility","created":"2021-07-01","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":"2210.02075","title":"On the Learning Mechanisms in Physical Reasoning","created":"2022-10-05","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":"2604.09415","title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","created":"2026-04-10","cited_by_count":9,"area":null},{"id":"2109.04683","title":"PIP: Physical Interaction Prediction via Mental Simulation with Span Selection","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2305.19550","title":"Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior","created":"2023-05-31","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":"2112.08001","title":"Autoencoder-based background reconstruction and foreground segmentation with background noise estimation","created":"2021-12-15","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":"2403.11237","title":"FORCE: Physics-aware Human-object Interaction","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2405.15916","title":"Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies","created":"2024-05-24","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":"2105.02799","title":"Object-centric Video Prediction without Annotation","created":"2021-05-06","cited_by_count":5,"area":null},{"id":"2207.02272","title":"Pretraining on Interactions for Learning Grounded Affordance Representations","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","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":"2601.09658","title":"Image2Garment: Simulation-ready Garment Generation from a Single Image","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2412.19847","title":"Symbolic Disentangled Representations for Images","created":"2024-12-25","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":"2403.10079","title":"Learning Physical Dynamics for Object-centric Visual Prediction","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2505.02071","title":"Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning","created":"2025-05-04","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":"2604.09072","title":"Overhang Tower: Resource-Rational Adaptation in Sequential Physical Planning","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2609.17112","title":"Not Another Text Benchmark: Putting the \"Visual\" Back in Visual Question Answering for Large Video Models","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}