TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

Year
2025
Type(s)
Author(s)
Zheng, Ruijie, Yongyuan Liang, Shuaiyi Huang, Jianfeng Gao, Hal Daum ́e III, Andrey Kolobov, Furong Huang, and Jianwei Yang.
Source
The Thirteenth International Conference on Learning Representations (ICLR), 2025.
BibTeX
BibTeX