{"total":85,"rows":[{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"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":"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":"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":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"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":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"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":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"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":"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":"2506.07865","title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","created":"2025-06-09","cited_by_count":13,"area":null},{"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":"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":"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":"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":"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":"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":"2311.18296","title":"Perceptual Group Tokenizer: Building Perception with Iterative Grouping","created":"2023-11-30","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":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4,"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":"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":"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":"2506.16129","title":"Neurosymbolic Object-Centric Learning with Distant Supervision","created":"2025-06-19","cited_by_count":2,"area":null},{"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":"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},{"id":"2406.18220","title":"Guiding Video Prediction with Explicit Procedural Knowledge","created":"2024-06-26","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":"2409.03553","title":"Organized Grouped Discrete Representation for Object-Centric Learning","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2502.08987","title":"Neural Force Field: Few-shot Learning of Generalized Physical Reasoning","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2502.11655","title":"TextOCVP: Object-Centric Video Prediction with Language Guidance","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2506.13803","title":"Causality in the human niche: lessons for machine learning","created":"2025-06-13","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":"2605.26104","title":"EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding","created":"2026-05-25","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":"2410.04940","title":"Next state prediction gives rise to entangled, yet compositional representations of objects","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2506.19621","title":"VideoPCDNet: Video Parsing and Prediction with Phase Correlation Networks","created":"2025-06-24","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":"2508.06335","title":"ViPro-2: Unsupervised State Estimation via Integrated Dynamics for Guiding Video Prediction","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.02032","title":"ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2512.15493","title":"Soft Geometric Inductive Bias for Object Centric Dynamics","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2602.01844","title":"CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.04941","title":"Improving Set Function Approximation with Quasi-Arithmetic Neural Networks","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.13912","title":"Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.16388","title":"ChronoSC: Task-Oriented Semantic Communication via Temporal-to-Color Encoding","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27696","title":"Structure over Pixels: Learning Variable-Length Visual Programs","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.30211","title":"Cycle Consistency in Video Object-Centric Learning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30942","title":"PRISM: Progressive Reasoning through Iterative Slot Memory for Vision","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.31508","title":"Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.30442","title":"The FIL Hypothesis: Inductive Biases Help with Kernel Engineering","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.04866","title":"Persistent Object Narratives for Token-Efficient Video Language Models","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.30743","title":"From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia","created":"2026-09-25","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}