{"total":90,"rows":[{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071,"area":"mllm"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2207.13298","title":"Is Attention All That NeRF Needs?","created":"2022-07-27","cited_by_count":113,"area":null},{"id":"2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90,"area":"diffusion"},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85,"area":"diffusion"},{"id":"2305.01278","title":"VPGTrans: Transfer Visual Prompt Generator across LLMs","created":"2023-05-02","cited_by_count":80,"area":"mllm"},{"id":"2310.03020","title":"Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models","created":"2023-10-04","cited_by_count":79,"area":"diffusion"},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79,"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":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73,"area":null},{"id":"2312.04551","title":"Free3D: Consistent Novel View Synthesis without 3D Representation","created":"2023-12-07","cited_by_count":72,"area":null},{"id":"2312.06725","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","created":"2023-12-11","cited_by_count":72,"area":"diffusion"},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2407.00959","title":"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving","created":"2024-07-01","cited_by_count":56,"area":"wm"},{"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":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"id":"2211.14306","title":"RUST: Latent Neural Scene Representations from Unposed Imagery","created":"2022-11-25","cited_by_count":43,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2402.16936","title":"Disentangled 3D Scene Generation with Layout Learning","created":"2024-02-26","cited_by_count":33,"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":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2310.08587","title":"Pseudo-Generalized Dynamic View Synthesis from a Video","created":"2023-10-12","cited_by_count":27,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2305.17102","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2412.07770","title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","created":"2024-12-10","cited_by_count":23,"area":null},{"id":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20,"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":"2312.08568","title":"NViST: In the Wild New View Synthesis from a Single Image with Transformers","created":"2023-12-13","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":"2312.06561","title":"Inferring Hybrid Neural Fluid Fields from Videos","created":"2023-12-11","cited_by_count":18,"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":"2301.13197","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","created":"2023-01-30","cited_by_count":16,"area":null},{"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":"2308.02840","title":"Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis","created":"2023-08-05","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":"2404.09736","title":"FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features","created":"2024-04-15","cited_by_count":14,"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":"2305.08810","title":"AutoRecon: Automated 3D Object Discovery and Reconstruction","created":"2023-05-15","cited_by_count":13,"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":"2502.15336","title":"Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions","created":"2025-02-21","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":"2402.07376","title":"Unsupervised Discovery of Object-Centric Neural Fields","created":"2024-02-12","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":"2310.06020","title":"DyST: Towards Dynamic Neural Scene Representations on Real-World Videos","created":"2023-10-09","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":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2309.13248","title":"Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation","created":"2023-09-23","cited_by_count":9,"area":null},{"id":"2304.00947","title":"RePAST: Relative Pose Attention Scene Representation Transformer","created":"2023-04-03","cited_by_count":8,"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":"2402.18277","title":"Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing","created":"2024-02-28","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":"2301.04101","title":"Neural Radiance Field Codebooks","created":"2023-01-10","cited_by_count":7,"area":null},{"id":"2307.03704","title":"Equivariant Single View Pose Prediction Via Induced and Restricted Representations","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2503.15141","title":"Object-Centric Pretraining via Target Encoder Bootstrapping","created":"2025-03-19","cited_by_count":6,"area":"synth"},{"id":"2402.05627","title":"Binding Dynamics in Rotating Features","created":"2024-02-08","cited_by_count":5,"area":null},{"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":"2506.01778","title":"unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2602.20685","title":"RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space","created":"2026-02-24","cited_by_count":4,"area":"wm"},{"id":"2301.05747","title":"Laser: Latent Set Representations for 3D Generative Modeling","created":"2023-01-13","cited_by_count":3,"area":null},{"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":"2405.03864","title":"Learning Planning Abstractions from Language","created":"2024-05-06","cited_by_count":3,"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":"2302.03288","title":"Object-Centric Scene Representations using Active Inference","created":"2023-02-07","cited_by_count":2,"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":"2401.02241","title":"Slot-guided Volumetric Object Radiance Fields","created":"2024-01-04","cited_by_count":2,"area":null},{"id":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","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":"2606.23436","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":"2402.02906","title":"ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis","created":"2024-02-05","cited_by_count":1,"area":"diffusion"},{"id":"2509.06336","title":"Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofing","created":"2025-09-08","cited_by_count":1,"area":"mllm"},{"id":"2509.24441","title":"NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2305.09566","title":"Ray-Patch: An Efficient Querying for Light Field Transformers","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2601.22529","title":"SHED Light on Segmentation for Dense Prediction","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.31535","title":"RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.08249","title":"HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.19765","title":"Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.21636","title":"Semantic Slots for Video Object-Centric Learning","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.19463","title":"ParticleSplat: Self-supervised Object-centric Latent Particle Splatting","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.24127","title":"Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}