arXiv:2604. 10579v2 Announce Type: replace-cross Abstract: Despite the recent success of modern imitation learning methods in robot manipulation, their performance is often constrained by geometric variations due to limited data diversity.
By Jiawei Zhang, Kaizhe Hu, Yingqian Huang, Yuanchen Ju, Zhengrong Xue, Huazhe Xu
FuncBridge is a two‑stage framework that addresses functional generalization in robotics by decoupling functional reasoning from action execution. It learns to predict generalizable 2D keypoint trajectories from action‑free data and then grounds these trajectories into robot actions with limited demonstrations. Across a benchmark of ten tools and three functions—hitting, sweeping, and hooking—FuncBridge outperforms state‑of‑the‑art methods on unseen tools in both simulation and real‑world tests.
By Chuhao Zhou, Liquan Wang, Shuxin Cao, Xiangyu Chen, Yuxuan Hu, Boyu Ma, Animesh Garg, Jianfei Yang
KeyGen is a framework that learns canonical 3D keypoints from point clouds to create structured, object‑centric representations for policy learning in robotic manipulation. By conditioning a visuomotor diffusion policy on these keypoints and object geometry, it predicts full manipulation trajectories that maintain geometric correspondence across different object instances. Experiments on a photorealistic simulation benchmark with three tasks show that KeyGen outperforms prior methods on both seen and unseen objects, scales with more demonstrations, remains robust to rescaling, and performs well in real‑world manipulation.
By Shuxin Cao, Liquan Wang, Masoud Moghani, Benjamin Joffe, Animesh Garg
arXiv:2606. 28813v1 Announce Type: cross Abstract: Human videos are a scalable source of supervision for robot manipulation, as they are abundant and naturally capture rich object interactions.
By Shuo Cheng, Chuye Zhang, Alfred Cueva, Caelan Garrett, Ajay Mandlekar, Danfei Xu
UniCross proposes a unified framework that models the four canonical dexterous manipulation skills—grasping, relocation, in-hand rotation, and in-hand translation—within a single formulation sharing state, action spaces, and objective structure. This approach enables distillation of a single cross-skill policy that performs well across all skills, generalizes to unseen objects, remains robust to disturbances, and can chain skills into long-horizon manipulation without policy switching. The framework also transfers effectively across different hand morphologies, suggesting that these skills can be viewed as instantiations of a shared task formulation.
By Hui Zhang, Julian Ferchow, Jie Song, Mirko Meboldt
arXiv:2606. 08530v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments.
By Yuan Zhang, Shiqi Zhang, Yedong Shen, Shuai Dong, Jiajun Deng, Xin Zhang, Yuxuan Gao, Jiajia Wu, Xin Nie, Zhiyuan Cheng, Jianmin Ji, Yanyong Zhang, Xingyi Zhang, Jia Pan