10 papers
FreeSpeed: Training-Free Speed Control for Generative Robot Policies
Yuxuan Hu, Shilin Shan, Qiheng Wang +4
Online control of execution speed is essential for deploying robot policies in real-world scenarios, as robots may need to speed up under time constraints or slow down to facilitat…
EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy
Zhirui Fang, Qingchi Yu, Ziyang Chen +18
A robot's effective ``mind'' need not reside in a single policy. It can emerge when specialized components perceive, reason, predict, act, verify, and remember within a shared orch…
FuncBridge: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning
Chuhao Zhou, Liquan Wang, Shuxin Cao +5
While humans readily repurpose a book, a stone, or a shoe to drive a nail, robots trained on specific tools fail to transfer the same function to novel ones -- a gap we formalize a…
ResCue: Residual Spatial Cueing for Language-Conditioned Imitation Learning
Yanzhe Tang, Xinyu Shao, Yuxuan Hu +8
Visual imitation policies must learn which image regions matter for action, whether applying the same operation to different objects or selecting a language-specified target. We in…
Rethinking Implicit Spatial Representation in Visuomotor Policy Learning
Xiangyu Chen, Yuxuan Hu, Chuhao Zhou +1
Generative model-based imitation learning has become a widely adopted paradigm for robotic manipulation, where policy performance depends critically on the conditioned visual repre…
MARS Policy: Multimodality Only When It Matters
Jindou Jia, Tuo An, Yuxuan Hu +7
Imitation learning has become a cornerstone for solving complex robotic manipulation tasks. In particular, multimodality, which enables robots to capture diverse yet valid behavior…
FLASH: Efficient Visuomotor Policy via Sparse Sampling
Jiaqi Bai, Jindou Jia, Yuxuan Hu +5
Generative models such as diffusion and flow matching have become dominant paradigms for visuomotor policy learning, yet their reliance on iterative denoising incurs high inference…
Trace-Focused Diffusion Policy for Multi-Modal Action Disambiguation in Long-Horizon Robotic Manipulation
Yuxuan Hu, Xiangyu Chen, Chuhao Zhou +4
Generative model-based policies have shown strong performance in imitation-based robotic manipulation by learning action distributions from demonstrations. However, in long-horizon…
Action-to-Action Flow Matching
Jindou Jia, Gen Li, Xiangyu Chen +5
Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice o…
DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization
Yikai Tang, Haoran Geng, Jindou Jia +5
Imitation learning has emerged as a crucial approach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy gen…