BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation

作者：Yucheng Hu, Jianke Zhang, Yuanfei Luo, Yanjiang Guo, Xiaoyu Chen, Xinshu Sun, Kun Feng, Qingzhou Lu, Sheng Chen, Yangang Zhang, Wei Li, Jianyu Chen · 单位：Tsinghua University, ByteDance Seed · 会议/期刊：arXiv · 日期：2026-02-10 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization