Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
Guangqi Jiang, Yifei Sun, Tao Huang, Huanyu Li, Yongyuan Liang, Huazhe Xu
2025年份
11顶会引用
摘要
DexArt MCR (ours) R3M R3M-DROID MVP VC-1 HRP Figure 2 : Correlation between manipulation centricity and downstream performance. Our findings reveal that (1) the proposed metric of manipulation centricity strongly correlates with the downstream performance of robotic representations, and (2) using the robot dataset DROID yields greater benefits for robotic representations than human datasets. (3) These insights motivate our method, MCR, which leverages dynamics labels from the robot dataset to further enhance manipulation centricity and downstream performance.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper11
- TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment VideosSeungjae Lee, Yoonkyo Jung, Inkook Chun, Yao-Chih Lee 等CVPR 2026 · 被引用 17 次
- Cross-Hand Latent Representation for Vision-Language-Action ModelsGuangqi Jiang, Yutong Liang, Jianglong Ye, Jia-Yang Huang 等CVPR 2026 · 被引用 14 次
- When would Vision-Proprioception Policies Fail in Robotic Manipulation?Jingxian Lu, Wenke Xia, Yuxuan Wu, Zhiwu Lu 等ICLR 2026 · 被引用 11 次
- Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot LearningQiwei Liang, Boyang Cai, Minghao Lai, Sitong Zhuang 等CVPR 2026 · 被引用 6 次
- Contact-Aware Neural DynamicsChangwei Jing, Jai Krishna Bandi, Jianglong Ye, Yan Duan 等CVPR 2026 · 被引用 5 次
它引用的顶会 Paper17
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn 等ICLR 2021 · 被引用 21,477 次
- Data-Efficient Image Recognition with Contrastive Predictive CodingOlivier J. HénaffICML 2020 · 被引用 1,553 次
- CURL: Contrastive Unsupervised Representations for Reinforcement LearningMichael Laskin, Aravind Srinivas, Pieter AbbeelICML 2020 · 被引用 1,261 次
- Masked Autoencoders As Spatiotemporal LearnersChristoph Feichtenhofer, Haoqi Fan, Yanghao Li, Kaiming HeNeurIPS 2022 · 被引用 690 次
- Decoupling Representation Learning from Reinforcement LearningAdam Stooke, Kimin Lee, Pieter Abbeel, Michael LaskinICML 2021 · 被引用 389 次
相关 Paper
- Learning Object-Centric Motion Priors from Human for Robotic Dexterous ManipulationZhengdong Hong, Guofeng ZhangAAAI 2026
- EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric FlowYixiang Chen, Peiyan Li, Yan Huang, Jiabing Yang 等ICCV 2025 · 被引用 2 次
- Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal ModelingYuze Hao, Jianrong Zhang, Tao Zhuo, Fuan Wen 等AAAI 2024 · 被引用 7 次
- HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal DataRuizhe Liu, Pei Zhou, Qian Luo, Li Sun 等NeurIPS 2025 · 被引用 2 次
- Human2Robot: Learning Robot Actions from Paired Human-Robot VideosSicheng Xie, Haidong Cao, Zejia Weng, Zhen Xing 等AAAI 2026 · 被引用 15 次
