{"total":166,"rows":[{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"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":"2210.09996","title":"Perceptual Grouping in Contrastive Vision-Language Models","created":"2022-10-18","cited_by_count":82,"area":"mllm"},{"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":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"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":"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":"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":"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":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2406.09196","title":"Adaptive Slot Attention: Object Discovery with Dynamic Slot Number","created":"2024-06-13","cited_by_count":34,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31,"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":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2406.09292","title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","created":"2024-06-13","cited_by_count":30,"area":"diffusion"},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29,"area":null},{"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":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"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":"2308.09951","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","created":"2023-08-19","cited_by_count":20,"area":null},{"id":"2511.11478","title":"Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective","created":"2025-11-14","cited_by_count":20,"area":"vla"},{"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":"2211.09771","title":"Boosting Object Representation Learning via Motion and Object Continuity","created":"2022-11-16","cited_by_count":17,"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":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","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":"2302.08023","title":"Object-centric Learning with Cyclic Walks between Parts and Whole","created":"2023-02-16","cited_by_count":16,"area":"lr"},{"id":"2305.15001","title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2307.08027","title":"Multi-Object Discovery by Low-Dimensional Object Motion","created":"2023-07-16","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":"2406.09949","title":"Neural Concept Binder","created":"2024-06-14","cited_by_count":14,"area":"lr"},{"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":"2407.17929","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","created":"2024-07-25","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":"2303.01526","title":"Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2309.09858","title":"Unsupervised Open-Vocabulary Object Localization in Videos","created":"2023-09-18","cited_by_count":13,"area":"mllm"},{"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":"2507.03298","title":"Dyn-O: Building Structured World Models with Object-Centric Representations","created":"2025-07-04","cited_by_count":13,"area":"wm"},{"id":"2508.10731","title":"Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction","created":"2025-08-14","cited_by_count":13,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2408.06697","title":"SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields","created":"2024-08-13","cited_by_count":12,"area":null},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"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":"2212.06795","title":"GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation","created":"2022-12-13","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":"2312.11463","title":"Appearance-Based Refinement for Object-Centric Motion Segmentation","created":"2023-12-18","cited_by_count":11,"area":null},{"id":"2411.05927","title":"Moving Off-the-Grid: Scene-Grounded Video Representations","created":"2024-11-08","cited_by_count":11,"area":null},{"id":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11,"area":null},{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2505.20772","title":"MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2311.17893","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","created":"2023-11-29","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":"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":"2406.07141","title":"Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2305.18890","title":"Sensitivity of Slot-Based Object-Centric Models to their Number of Slots","created":"2023-05-30","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":"2405.17283","title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","created":"2024-05-27","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":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","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":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2210.02159","title":"Differentiable Mathematical Programming for Object-Centric Representation Learning","created":"2022-10-05","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":"2411.01801","title":"Bootstrapping Top-down Information for Self-modulating Slot Attention","created":"2024-11-04","cited_by_count":6,"area":"lr"},{"id":"2411.19141","title":"On Moving Object Segmentation from Monocular Video with Transformers","created":"2024-11-28","cited_by_count":6,"area":null},{"id":"2503.18695","title":"OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2505.11563","title":"Object-Centric Representations Improve Policy Generalization in Robot Manipulation","created":"2025-05-16","cited_by_count":6,"area":null},{"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":"2404.12509","title":"Compositional Neural Textures","created":"2024-04-18","cited_by_count":5,"area":null},{"id":"2405.16493","title":"Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception","created":"2024-05-26","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":"2305.17262","title":"Im-Promptu: In-Context Composition from Image Prompts","created":"2023-05-26","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":"2311.18296","title":"Perceptual Group Tokenizer: Building Perception with Iterative Grouping","created":"2023-11-30","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":"2407.20908","title":"Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering","created":"2024-07-30","cited_by_count":4,"area":null},{"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":"2305.00393","title":"DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization","created":"2023-04-30","cited_by_count":3,"area":null},{"id":"2306.02577","title":"Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2311.02633","title":"The Background Also Matters: Background-Aware Motion-Guided Objects Discovery","created":"2023-11-05","cited_by_count":3,"area":null}],"next_cursor":"100"}