X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning

作者：Maanping Shao, Feihong Zhang, Gu Zhang, Baiye Cheng, Zhengrong Xue, ResNet Avg. Task Success Rates · 单位：Huazhong University of Science and Technology, the Institute for Interdisciplinary Information Sci · 会议/期刊：arXiv · 日期：2026-01-16 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Vision Action Models / Image-Action Models