5 papers
A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
Yu Lei, Minghuan Liu, Abhiram Maddukuri +2
Co-training, which combines limited in-domain real-world data with abundant surrogate data such as simulation or cross-embodiment robot data, is widely used for training generative…
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
Haotong Lin, Sida Peng, Jingxiao Chen +7
Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation m…
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
Huihan Liu, Changyeon Kim, Bo Liu +2
Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned on…
What Matters in Building Vision-Language-Action Models for Generalist Robots
Xinghang Li, Peiyan Li, Long Qian +10
To utilize Foundation Vision Language Models (VLMs) for robotic tasks and motion planning, the community has proposed different methods for injecting action components into VLMs an…
Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots
Minghuan Liu, Zhengbang Zhu, Xiaoshen Han +12
Modern robotic manipulation primarily relies on visual observations in a 2D color space for skill learning but suffers from poor generalization. In contrast, humans, living in a 3D…