A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference

Zhuoran Song, Haozhe Jiang, Chunyu Qi, Minnan Pei, Gang Li, Xiaoyao Liang, Haibing GuanarXiv 2026 · DOI

BibTeX
@misc{song2026motion,
  author = {Zhuoran Song and Haozhe Jiang and Chunyu Qi and Minnan Pei and Gang Li and Xiaoyao Liang and Haibing Guan},
  title = {{A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference}},
  year = {2026},
  eprint = {2607.24148},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.24148},
}

Loading related content...

Figure