ドリフト対応ポストトレーニング量子化による効率的な視覚言語行動モデル
DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
視覚言語行動モデル(VLA)の量子化時に生じる時間的誤差蓄積による動作ドリフトを解決するため、ドリフト対応PTQ(DA-PTQ)を提案。クロススペース表現補償と動作駆動混合精度割り当てにより、低ビットでも高精度な制御を実現。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Siyuan Xu, Tianshi Wang, Fengling Li, Lei Zhu, Heng Tao Shen
分類: cs.RO, cs.MM
原文アブストラクト
Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands. While Post-Training Quantization (PTQ) provides an efficient solution, directly applying PTQ to VLAs often results in severe performance degradation during sequential control. We identify temporal error accumulation as a key factor, where quantization perturbations at the vision-language-to-action interface are progressively amplified, leading to kinematic drift in executed trajectories. To address this issue, we propose Drift-Aware Post-Training Quantization (DA-PTQ), which formulates quantization as a drift-aware optimization problem over sequential decision processes. DA-PTQ consists of two components: (1) Cross-Space Representation Compensation, which mitigates structured distortions between multimodal representations and action space to improve action consistency, and (2) Motion-Driven Mixed-Precision Allocation, which assigns bit-widths by minimizing trajectory-level motion errors. Extensive experiments show that DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings, enabling practical deployment of VLAs on resource-limited robotic platforms.
