{"list":"other","total":54,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"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":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"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":"2310.10639","title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","created":"2023-10-16","cited_by_count":269},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"1612.00404","title":"Learning Shape Abstractions by Assembling Volumetric Primitives","created":"2016-12-01","cited_by_count":181},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2507.05331","title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","created":"2025-07-07","cited_by_count":129},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119},{"id":"2011.09584","title":"ACRONYM: A Large-Scale Grasp Dataset Based on Simulation","created":"2020-11-18","cited_by_count":117},{"id":"1811.08988","title":"Supervised Fitting of Geometric Primitives to 3D Point Clouds","created":"2018-11-22","cited_by_count":91},{"id":"2401.03360","title":"Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models","created":"2023-10-13","cited_by_count":91},{"id":"2502.20900","title":"DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping","created":"2025-02-28","cited_by_count":89},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"2006.13205","title":"Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors","created":"2020-06-23","cited_by_count":62},{"id":"2310.14386","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","created":"2023-10-22","cited_by_count":61},{"id":"2503.03734","title":"OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction","created":"2025-03-05","cited_by_count":54},{"id":"2306.10007","title":"Robot Learning with Sensorimotor Pre-training","created":"2023-06-16","cited_by_count":51},{"id":"1708.04225","title":"Deep Object-Centric Representations for Generalizable Robot Learning","created":"2017-08-14","cited_by_count":50},{"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":"2407.18911","title":"HRP: Human Affordances for Robotic Pre-Training","created":"2024-07-26","cited_by_count":44},{"id":"2312.12444","title":"What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?","created":"2023-11-03","cited_by_count":39},{"id":"2307.05473","title":"Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives","created":"2023-07-11","cited_by_count":38},{"id":"2506.17198","title":"Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation","created":"2025-06-20","cited_by_count":24},{"id":"2011.08177","title":"A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects","created":"2020-11-16","cited_by_count":23},{"id":"2307.02427","title":"FOCUS: Object-Centric World Models for Robotics Manipulation","created":"2023-07-05","cited_by_count":17},{"id":"2405.05876","title":"Composable Part-Based Manipulation","created":"2024-05-09","cited_by_count":17},{"id":"2401.09939","title":"ICGNet: A Unified Approach for Instance-Centric Grasping","created":"2024-01-18","cited_by_count":16},{"id":"2503.06170","title":"Object-Centric World Model for Language-Guided Manipulation","created":"2025-03-08","cited_by_count":16},{"id":"2403.18062","title":"ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decomposition","created":"2024-03-26","cited_by_count":14},{"id":"1905.13153","title":"Grounding Language Attributes to Objects using Bayesian Eigenobjects","created":"2019-05-30","cited_by_count":8},{"id":"2402.05644","title":"FuncGrasp: Learning Object-Centric Neural Grasp Functions from Single Annotated Example Object","created":"2024-02-08","cited_by_count":6},{"id":"2307.15320","title":"Robust Visual Sim-to-Real Transfer for Robotic Manipulation","created":"2023-07-28","cited_by_count":5},{"id":"2410.08901","title":"SegGrasp: Zero-Shot Task-Oriented Grasping via Semantic and Geometric Guided Segmentation","created":"2024-10-11","cited_by_count":2}],"next_cursor":null}