{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"id":"2310.11441","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","created":"2023-10-17","cited_by_count":299},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133},{"id":"2311.01977","title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","created":"2023-11-03","cited_by_count":133},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124},{"id":"2403.08248","title":"CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models","created":"2024-03-13","cited_by_count":99},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"1911.07246","title":"IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks","created":"2019-11-17","cited_by_count":69},{"id":"2003.09754","title":"Learning 3D Part Assembly from a Single Image","created":"2020-03-21","cited_by_count":52},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48},{"id":"2205.14886","title":"Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors","created":"2022-05-30","cited_by_count":43},{"id":"2210.11463","title":"Breaking Bad: A Dataset for Geometric Fracture and Reassembly","created":"2022-10-20","cited_by_count":41},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41},{"id":"2402.19302","title":"DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly","created":"2024-02-29","cited_by_count":33},{"id":"2309.06810","title":"Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly","created":"2023-09-13","cited_by_count":28},{"id":"2302.01881","title":"IKEA-Manual: Seeing Shape Assembly Step by Step","created":"2023-02-03","cited_by_count":22},{"id":"2303.06163","title":"Category-Level Multi-Part Multi-Joint 3D Shape Assembly","created":"2023-03-10","cited_by_count":22},{"id":"2402.17464","title":"Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing","created":"2024-02-27","cited_by_count":19},{"id":"2309.16909","title":"ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility","created":"2023-09-29","cited_by_count":18},{"id":"2207.12572","title":"Translating a Visual LEGO Manual to a Machine-Executable Plan","created":"2022-07-25","cited_by_count":15},{"id":"2409.17126","title":"Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset","created":"2024-09-25","cited_by_count":15},{"id":"2112.10143","title":"RoboAssembly: Learning Generalizable Furniture Assembly Policy in a Novel Multi-robot Contact-rich Simulation Environment","created":"2021-12-19","cited_by_count":14},{"id":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","cited_by_count":12},{"id":"2404.17906","title":"VIEW: Visual Imitation Learning with Waypoints","created":"2024-04-27","cited_by_count":10},{"id":"2411.18011","title":"Manual-PA: Learning 3D Part Assembly from Instruction Diagrams","created":"2024-11-27","cited_by_count":7},{"id":"1809.06590","title":"Learning Universal Sentence Representations with Mean-Max Attention Autoencoder","created":"2018-09-18","cited_by_count":3}],"next_cursor":null}