{"total":109,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163,"area":null},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161,"area":null},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136,"area":"offlinerl"},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111,"area":null},{"id":"2110.05428","title":"Learning Temporally Causal Latent Processes from General Temporal Data","created":"2021-10-11","cited_by_count":98,"area":null},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87,"area":null},{"id":"2112.01983","title":"CoNeRF: Controllable Neural Radiance Fields","created":"2021-12-03","cited_by_count":65,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63,"area":null},{"id":"2206.08321","title":"Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning","created":"2022-06-16","cited_by_count":56,"area":null},{"id":"2010.09034","title":"Model-Based Inverse Reinforcement Learning from Visual Demonstrations","created":"2020-10-18","cited_by_count":52,"area":"offlinerl"},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45,"area":null},{"id":"2206.01634","title":"Reinforcement Learning with Neural Radiance Fields","created":"2022-06-03","cited_by_count":43,"area":null},{"id":"2307.01849","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","created":"2023-07-04","cited_by_count":40,"area":"diffusion"},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2104.02921","title":"Unsupervised Visual Attention and Invariance for Reinforcement Learning","created":"2021-04-07","cited_by_count":30,"area":null},{"id":"2106.07643","title":"Unsupervised Learning of Visual 3D Keypoints for Control","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2103.00375","title":"Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control","created":"2021-02-28","cited_by_count":24,"area":"offlinerl"},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2308.09987","title":"ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environment","created":"2023-08-19","cited_by_count":23,"area":null},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"id":"2107.08577","title":"Structured World Belief for Reinforcement Learning in POMDP","created":"2021-07-19","cited_by_count":21,"area":"wm"},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21,"area":null},{"id":"2210.06433","title":"Self-supervised video pretraining yields robust and more human-aligned visual representations","created":"2022-10-12","cited_by_count":20,"area":null},{"id":"2309.05098","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","created":"2023-09-10","cited_by_count":20,"area":null},{"id":"2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","created":"2021-12-02","cited_by_count":19,"area":null},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2205.15821","title":"Unsupervised Image Representation Learning with Deep Latent Particles","created":"2022-05-31","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":"2104.12149","title":"Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects","created":"2021-04-25","cited_by_count":17,"area":null},{"id":"2205.10636","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","created":"2022-05-21","cited_by_count":17,"area":null},{"id":"2104.14040","title":"Pushing it out of the Way: Interactive Visual Navigation","created":"2021-04-28","cited_by_count":16,"area":null},{"id":"2301.11520","title":"SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning","created":"2023-01-27","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":"2312.12791","title":"Model-Based Control with Sparse Neural Dynamics","created":"2023-12-20","cited_by_count":16,"area":null},{"id":"2404.13474","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","created":"2024-04-20","cited_by_count":16,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","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":"2202.00368","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2309.12969","title":"Detect Everything with Few Examples","created":"2023-09-22","cited_by_count":14,"area":null},{"id":"2107.08881","title":"Reasoning-Modulated Representations","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2404.07950","title":"Reinforcement Learning with Generalizable Gaussian Splatting","created":"2024-03-18","cited_by_count":13,"area":"deeprl"},{"id":"2305.04718","title":"The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2112.05068","title":"A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation","created":"2021-12-09","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":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2207.05054","title":"Demystifying Unsupervised Semantic Correspondence Estimation","created":"2022-07-11","cited_by_count":10,"area":null},{"id":"2410.12124","title":"Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames","created":"2024-10-15","cited_by_count":10,"area":"offlinerl"},{"id":"2110.04685","title":"Learning Visual Shape Control of Novel 3D Deformable Objects from Partial-View Point Clouds","created":"2021-10-10","cited_by_count":9,"area":null},{"id":"2104.04275","title":"GATSBI: Generative Agent-centric Spatio-temporal Object Interaction","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2202.00448","title":"Sim2Real Object-Centric Keypoint Detection and Description","created":"2022-02-01","cited_by_count":8,"area":null},{"id":"2302.10446","title":"Deep Reinforcement Learning Based on Local GNN for Goal-conditioned Deformable Object Rearranging","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2309.12312","title":"ForceSight: Text-Guided Mobile Manipulation with Visual-Force Goals","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2307.13640","title":"Optical Flow boosts Unsupervised Localization and Segmentation","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2104.03424","title":"Track, Check, Repeat: An EM Approach to Unsupervised Tracking","created":"2021-04-07","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":"2109.05928","title":"Vision-based system identification and 3D keypoint discovery using dynamics constraints","created":"2021-09-13","cited_by_count":5,"area":null},{"id":"2202.13604","title":"Generalizable task representation learning from human demonstration videos: a geometric approach","created":"2022-02-28","cited_by_count":5,"area":null},{"id":"2408.08160","title":"General-purpose Clothes Manipulation with Semantic Keypoints","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2205.15895","title":"From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2107.08067","title":"DeformerNet: A Deep Learning Approach to 3D Deformable Object Manipulation","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2205.06714","title":"Learning Keypoints from Synthetic Data for Robotic Cloth Folding","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2205.08316","title":"Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2309.09183","title":"CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2311.09350","title":"Generalizable Imitation Learning Through Pre-Trained Representations","created":"2023-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2403.16194","title":"Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery","created":"2024-03-24","cited_by_count":3,"area":"diffusion"},{"id":"2503.18671","title":"Structure-Aware Correspondence Learning for Relative Pose Estimation","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2202.13624","title":"Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning","created":"2022-02-28","cited_by_count":2,"area":null},{"id":"2302.10445","title":"Graph-Transporter: A Graph-based Learning Method for Goal-Conditioned Deformable Object Rearranging Task","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2310.04617","title":"SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2401.00104","title":"Causal State Distillation for Explainable Reinforcement Learning","created":"2023-12-30","cited_by_count":2,"area":null},{"id":"2408.08108","title":"Unsupervised Part Discovery via Dual Representation Alignment","created":"2024-08-15","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":"2507.07197","title":"Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":"deeprl"},{"id":"2106.07995","title":"Learning of feature points without additional supervision improves reinforcement learning from images","created":"2021-06-15","cited_by_count":1,"area":null},{"id":"2202.09006","title":"KINet: Unsupervised Forward Models for Robotic Pushing Manipulation","created":"2022-02-18","cited_by_count":1,"area":null},{"id":"2308.13178","title":"Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions","created":"2023-08-25","cited_by_count":1,"area":null},{"id":"2309.06621","title":"A Reinforcement Learning Approach for Robotic Unloading from Visual Observations","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2310.01404","title":"H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2310.10307","title":"Learning visual-based deformable object rearrangement with local graph neural networks","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2311.00923","title":"A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2401.09336","title":"To deform or not: treatment-aware longitudinal registration for breast DCE-MRI during neoadjuvant chemotherapy via unsupervised keypoints detection","created":"2024-01-17","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":"2406.12441","title":"Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2502.18615","title":"A Distributional Treatment of Real2Sim2Real for Object-Centric Agent Adaptation in Vision-Driven Deformable Linear Object Manipulation","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.11118","title":"Revealing Human Attention Patterns from Gameplay Analysis for Reinforcement Learning","created":"2025-04-15","cited_by_count":1,"area":"deeprl"},{"id":"2507.19983","title":"CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2106.05929","title":"Domain Specific Transporter Framework to Detect Fractures in Ultrasound","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2106.06987","title":"Learning the Imaging Landmarks: Unsupervised Key point Detection in Lung Ultrasound Videos","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2109.06346","title":"Physics Driven Domain Specific Transporter Framework with Attention Mechanism for Ultrasound Imaging","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2202.06036","title":"Neural NID Rules","created":"2022-02-12","cited_by_count":0,"area":null},{"id":"2209.12350","title":"Unsupervised Reward Shaping for a Robotic Sequential Picking Task from Visual Observations in a Logistics Scenario","created":"2022-09-25","cited_by_count":0,"area":null},{"id":"2209.15404","title":"Entropy-driven Unsupervised Keypoint Representation Learning in Videos","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2210.12278","title":"Sample Efficient Robot Learning with Structured World Models","created":"2022-10-21","cited_by_count":0,"area":"wm"}],"next_cursor":"100"}