Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance

作者：Yang Zhang, Chenwei Wang, Ouyang Lu, Yuan Zhao, Yunfei Ge, Zhenglong Sun, Xiu Li, Chi Zhang, Chenjia Bai, Xuelong Li · 单位：1]Institute of Artificial Intelligence, China Telecom, 2]Tsinghua University, 3]The Chinese University of Hong Kong, Shenzhen, 4]Northwestern Polytechnical University · 会议/期刊：arXiv preprint 2025 · 方向：监督微调 · 发布日期：2025-09-02