{"list":"other","total":64,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2103.14127","title":"Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes","created":"2021-03-25","cited_by_count":218},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"1707.03374","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","created":"2017-07-11","cited_by_count":167},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"1802.01557","title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning","created":"2018-02-05","cited_by_count":148},{"id":"2407.15208","title":"Flow as the Cross-Domain Manipulation Interface","created":"2024-07-21","cited_by_count":132},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"2212.04498","title":"VideoDex: Learning Dexterity from Internet Videos","created":"2022-12-08","cited_by_count":106},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85},{"id":"2209.08290","title":"Changer: Feature Interaction is What You Need for Change Detection","created":"2022-09-17","cited_by_count":79},{"id":"2011.05970","title":"Transformers for One-Shot Visual Imitation","created":"2020-11-11","cited_by_count":78},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61},{"id":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59},{"id":"2312.00775","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","created":"2023-12-01","cited_by_count":52},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52},{"id":"1910.13675","title":"Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly","created":"2019-10-30","cited_by_count":51},{"id":"2211.09786","title":"SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields","created":"2022-11-17","cited_by_count":51},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50},{"id":"2110.13423","title":"Towards More Generalizable One-shot Visual Imitation Learning","created":"2021-10-26","cited_by_count":49},{"id":"2211.09325","title":"TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation","created":"2022-11-17","cited_by_count":47},{"id":"2202.09400","title":"Equivariant Transporter Network","created":"2022-02-18","cited_by_count":46},{"id":"2011.10726","title":"Object Rearrangement Using Learned Implicit Collision Functions","created":"2020-11-21","cited_by_count":43},{"id":"2310.09289","title":"An Unbiased Look at Datasets for Visuo-Motor Pre-Training","created":"2023-10-13","cited_by_count":42},{"id":"2311.00926","title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","created":"2023-11-02","cited_by_count":41},{"id":"2409.08273","title":"Hand-Object Interaction Pretraining from Videos","created":"2024-09-12","cited_by_count":39},{"id":"2309.16118","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","created":"2023-09-28","cited_by_count":35},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34},{"id":"2108.12062","title":"Predicting Stable Configurations for Semantic Placement of Novel Objects","created":"2021-08-26","cited_by_count":24},{"id":"1710.00290","title":"Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks","created":"2017-10-01","cited_by_count":21},{"id":"2404.13478","title":"Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks","created":"2024-04-20","cited_by_count":19},{"id":"2304.09302","title":"CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation","created":"2023-04-18","cited_by_count":18},{"id":"2001.08481","title":"Learning Object Placements For Relational Instructions by Hallucinating Scene Representations","created":"2020-01-23","cited_by_count":16},{"id":"2006.15503","title":"Task-driven Perception and Manipulation for Constrained Placement of Unknown Objects","created":"2020-06-28","cited_by_count":12},{"id":"1907.02555","title":"Object Placement Planning and Optimization for Robot Manipulators","created":"2019-07-04","cited_by_count":9},{"id":"2202.10765","title":"Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks","created":"2022-02-22","cited_by_count":9},{"id":"2401.08973","title":"OCTO+: A Suite for Automatic Open-Vocabulary Object Placement in Mixed Reality","created":"2024-01-17","cited_by_count":6}],"next_cursor":null}