← All publications
MICRO, 2026LLM / VLA

VQVLA: Motion-Aware Vector Quantization with Computation Fusion for VLA Acceleration

Zhuoran Song, Haozhe Jiang, Chunyu Qi, Minnan Pei, Gang Li, Xiaoyao Liang and Haibing Guan

Overview

Motion-aware vector quantization and computation fusion for efficient vision-language-action models.

通过运动感知向量量化与计算融合,加速视觉语言动作模型(VLA)。

  • Vision-Language-Action
  • Vector quantization
  • Inference acceleration

MICRO, 2026. Public paper and code links will be added when available.

Research by Minnan Pei (裴旻楠) and collaborators · Email