{"total":90,"rows":[{"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":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77,"area":"diffusion"},{"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":"2402.08714","title":"PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models","created":"2024-02-13","cited_by_count":42,"area":"diffusion"},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"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":"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":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30,"area":"mllm"},{"id":"2408.08000","title":"MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing","created":"2024-08-15","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":"2402.09712","title":"Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement","created":"2024-02-15","cited_by_count":27,"area":"diffusion"},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20,"area":"lr"},{"id":"2306.06997","title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","created":"2023-06-12","cited_by_count":20,"area":null},{"id":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"id":"2510.24709","title":"Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?","created":"2025-10-28","cited_by_count":19,"area":null},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2306.08068","title":"DORSal: Diffusion for Object-centric Representations of Scenes et al","created":"2023-06-13","cited_by_count":16,"area":"diffusion"},{"id":"2310.12904","title":"Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey","created":"2023-10-19","cited_by_count":16,"area":null},{"id":"2406.01062","title":"Layout Agnostic Scene Text Image Synthesis with Diffusion Models","created":"2024-06-03","cited_by_count":14,"area":"diffusion"},{"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":"2405.00646","title":"Learning to Compose: Improving Object Centric Learning by Injecting Compositionality","created":"2024-05-01","cited_by_count":13,"area":"lr"},{"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":"2503.21747","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","created":"2025-03-27","cited_by_count":12,"area":null},{"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":"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":"2511.02225","title":"Learning Interactive World Model for Object-Centric Reinforcement Learning","created":"2025-11-04","cited_by_count":11,"area":"wm"},{"id":"2312.08825","title":"Guided Diffusion from Self-Supervised Diffusion Features","created":"2023-12-14","cited_by_count":9,"area":"diffusion"},{"id":"2410.11251","title":"Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning","created":"2024-10-15","cited_by_count":9,"area":"deeprl"},{"id":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2412.10275","title":"TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation","created":"2024-12-13","cited_by_count":7,"area":null},{"id":"2505.17726","title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2602.16229","title":"Factored Latent Action World Models","created":"2026-02-18","cited_by_count":7,"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":"2503.15141","title":"Object-Centric Pretraining via Target Encoder Bootstrapping","created":"2025-03-19","cited_by_count":6,"area":"synth"},{"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":"2402.05627","title":"Binding Dynamics in Rotating Features","created":"2024-02-08","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":"2305.17262","title":"Im-Promptu: In-Context Composition from Image Prompts","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2309.12862","title":"Associative Transformer","created":"2023-09-22","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":"2410.18809","title":"Learning Global Object-Centric Representations via Disentangled Slot Attention","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2506.02964","title":"FORLA: Federated Object-centric Representation Learning with Slot Attention","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2601.01224","title":"Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment","created":"2026-01-03","cited_by_count":3,"area":"diffusion"},{"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":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","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":"2407.02386","title":"OpenSlot: Mixed Open-Set Recognition with Object-Centric Learning","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2407.05616","title":"Explainable Image Recognition via Enhanced Slot-attention Based Classifier","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2411.17438","title":"Object-centric proto-symbolic behavioural reasoning from pixels","created":"2024-11-26","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":"2503.09679","title":"DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2507.01882","title":"Future Slot Prediction for Unsupervised Object Discovery in Surgical Video","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2510.23956","title":"Neural USD: An object-centric framework for iterative editing and control","created":"2025-10-28","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":"2403.17664","title":"DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2411.00402","title":"Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection","created":"2024-11-01","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":"2510.21402","title":"Disentangled Representation Learning via Modular Compositional Bias","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2601.06604","title":"Object-Centric World Models Meet Monte Carlo Tree Search","created":"2026-01-10","cited_by_count":1,"area":"wm"},{"id":"2602.07544","title":"MUFASA: A Multi-Layer Framework for Slot Attention","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2606.23920","title":"Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate","created":"2026-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2507.20855","title":"Compositional Video Synthesis by Temporal Object-Centric Learning","created":"2025-07-28","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":"2509.09298","title":"Learning Object-Centric Representations in SAR Images with Multi-Level Feature Fusion","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2512.02685","title":"Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.18192","title":"Multi-Part Object Representations via Graph Structures and Co-Part Discovery","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.12936","title":"QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.07532","title":"Evaluating Object-Centric Models beyond Object Discovery","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.16689","title":"Are Object-Centric Representations Better At Compositional Generalization?","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2602.22621","title":"CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.02063","title":"ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.11246","title":"When Slots Compete: Slot Merging in Object-Centric Learning","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.19480","title":"Deep Sprite-based Image Models: An Analysis","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.12021","title":"What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.05325","title":"CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.11196","title":"Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders","created":"2026-07-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.17414","title":"SlotDiT: Object-Centric Representations for Diffusion Transformers","created":"2026-09-15","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}