arXiv · 2026 · Preprint

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, Yuke Zhu

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Date
2026-03-04
Citations
15
arXiv
2603.03818
Cite
@misc{liu2026pretrained,
  title = {Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning},
  author = {Huihan Liu and Changyeon Kim and Bo Liu and Minghuan Liu and Yuke Zhu},
  year = {2026},
  eprint = {2603.03818},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.03818},
}