{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139},{"id":"2406.08545","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","created":"2024-06-12","cited_by_count":137},{"id":"2311.01977","title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","created":"2023-11-03","cited_by_count":133},{"id":"2502.05485","title":"HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation","created":"2025-02-08","cited_by_count":130},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2510.03342","title":"Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer","created":"2025-10-02","cited_by_count":87},{"id":"2407.10353","title":"UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers","created":"2024-07-14","cited_by_count":75},{"id":"2505.21864","title":"DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation","created":"2025-05-28","cited_by_count":66},{"id":"2409.19499","title":"FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset","created":"2024-09-29","cited_by_count":40},{"id":"2306.16605","title":"KITE: Keypoint-Conditioned Policies for Semantic Manipulation","created":"2023-06-29","cited_by_count":39},{"id":"2505.07813","title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","created":"2025-05-12","cited_by_count":38},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2503.13446","title":"MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation","created":"2025-03-17","cited_by_count":34},{"id":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31},{"id":"2406.19464","title":"ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data","created":"2024-06-27","cited_by_count":31},{"id":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27},{"id":"2411.07223","title":"Grounding Video Models to Actions through Goal Conditioned Exploration","created":"2024-11-11","cited_by_count":26},{"id":"2405.04370","title":"Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos","created":"2024-05-07","cited_by_count":21},{"id":"2411.03682","title":"LEGATO: Cross-Embodiment Imitation Using a Grasping Tool","created":"2024-11-06","cited_by_count":18},{"id":"2603.22003","title":"VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models","created":"2026-03-23","cited_by_count":17},{"id":"2602.06643","title":"Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations","created":"2026-02-06","cited_by_count":12},{"id":"2510.02614","title":"UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies","created":"2025-10-02","cited_by_count":11},{"id":"2510.08022","title":"FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset","created":"2025-10-09","cited_by_count":11},{"id":"2403.05046","title":"EgoPAT3Dv2: Predicting 3D Action Target from 2D Egocentric Vision for Human-Robot Interaction","created":"2024-03-08","cited_by_count":10},{"id":"2405.20030","title":"EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos","created":"2024-05-30","cited_by_count":8},{"id":"2604.24921","title":"Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System","created":"2026-04-27","cited_by_count":6}],"next_cursor":null}