CommentsShaoxiong Yao and Sicong Pan have equal contributions. Publication to appear in IEEE International Conference on Robotics and Automation (ICRA), 2025
Comments6 pages, 4 figures, To be appear in the proceedings of 2019 4th International Conference on Robotics and Automation Engineering. Singapore November 22-24, 2019
CommentsAccepted in IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019. arXiv admin note: text overlap with arXiv:1905.04531
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
VLAFlow:通过协同训练和未来潜在对齐的视觉-语言-动作模型统一训练框架
Guoyang Xia, Fengfa Li, Hongjin Ji, Lei Ren, Fangxiang Feng, Kun Zhan, Yan Xie
机构
*
Li Auto Inc.(理想汽车)
;
School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)
;
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))