{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2506.21539","title":"WorldVLA: Towards Autoregressive Action World Model","created":"2025-06-26","cited_by_count":367},{"id":"2402.10885","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","created":"2024-02-16","cited_by_count":282},{"id":"2504.02792","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","created":"2025-04-03","cited_by_count":240},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2210.02697","title":"DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation","created":"2022-10-06","cited_by_count":137},{"id":"2407.15208","title":"Flow as the Cross-Domain Manipulation Interface","created":"2024-07-21","cited_by_count":132},{"id":"2303.00938","title":"UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy","created":"2023-03-02","cited_by_count":124},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2210.04887","title":"In-Hand Object Rotation via Rapid Motor Adaptation","created":"2022-10-10","cited_by_count":118},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108},{"id":"2304.00464","title":"UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning","created":"2023-04-02","cited_by_count":107},{"id":"1502.03143","title":"Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols","created":"2015-02-10","cited_by_count":99},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99},{"id":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79},{"id":"2404.16823","title":"Learning Visuotactile Skills with Two Multifingered Hands","created":"2024-04-25","cited_by_count":76},{"id":"2104.09194","title":"Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator","created":"2021-04-19","cited_by_count":71},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"2407.04689","title":"RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation","created":"2024-07-05","cited_by_count":58},{"id":"2312.00775","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","created":"2023-12-01","cited_by_count":52},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48},{"id":"2407.11385","title":"Omnigrasp: Grasping Diverse Objects with Simulated Humanoids","created":"2024-07-16","cited_by_count":46},{"id":"2402.02500","title":"Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning","created":"2024-02-04","cited_by_count":45},{"id":"2412.01791","title":"DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands","created":"2024-11-27","cited_by_count":45},{"id":"2410.23004","title":"DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes","created":"2024-10-30","cited_by_count":44},{"id":"2407.02274","title":"DextrAH-G: Pixels-to-Action Dexterous Arm-Hand Grasping with Geometric Fabrics","created":"2024-07-02","cited_by_count":42},{"id":"2510.05070","title":"ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning","created":"2025-10-06","cited_by_count":41},{"id":"2510.08568","title":"NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos","created":"2025-10-09","cited_by_count":40},{"id":"2002.01530","title":"Deep Differentiable Grasp Planner for High-DOF Grippers","created":"2020-02-04","cited_by_count":39},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38},{"id":"2506.06199","title":"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model","created":"2025-06-06","cited_by_count":37},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34},{"id":"2507.13097","title":"GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training","created":"2025-07-17","cited_by_count":32},{"id":"2502.04307","title":"DexterityGen: Foundation Controller for Unprecedented Dexterity","created":"2025-02-06","cited_by_count":29},{"id":"2407.18902","title":"Lessons from Learning to Spin \"Pens\"","created":"2024-07-26","cited_by_count":26},{"id":"2511.15200","title":"VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation","created":"2025-11-19","cited_by_count":25},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25},{"id":"2507.22885","title":"Viser: Imperative, Web-based 3D Visualization in Python","created":"2025-07-30","cited_by_count":23},{"id":"2503.16806","title":"DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation","created":"2025-03-21","cited_by_count":22},{"id":"2508.11002","title":"3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation","created":"2025-08-14","cited_by_count":20},{"id":"2506.20668","title":"DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy","created":"2025-06-25","cited_by_count":19},{"id":"2502.09614","title":"DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References","created":"2025-02-13","cited_by_count":17},{"id":"2601.07823","title":"Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions","created":"2026-01-12","cited_by_count":13},{"id":"2509.09671","title":"Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration","created":"2025-09-11","cited_by_count":11},{"id":"2506.09366","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","created":"2025-06-11","cited_by_count":9},{"id":"2510.08556","title":"DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model","created":"2025-10-09","cited_by_count":9},{"id":"2502.17894","title":"FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real","created":"2025-02-25","cited_by_count":5},{"id":"2509.16434","title":"End-to-end RL Improves Dexterous Grasping Policies","created":"2025-09-19","cited_by_count":5},{"id":"2512.24210","title":"GR-Dexter Technical Report","created":"2025-12-30","cited_by_count":5},{"id":"2310.05717","title":"STOPNet: Multiview-based 6-DoF Suction Detection for Transparent Objects on Production Lines","created":"2023-10-09","cited_by_count":2},{"id":"2511.07418","title":"Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields","created":"2025-11-10","cited_by_count":2}],"next_cursor":null}