効率的な視覚言語行動推論のための時間的冗長性の削減
Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference
VLAモデルの推論遅延を減らすため、視覚エンコーディングと拡散サンプリングの時間的冗長性を削減するシステムレベルの高速化手法を提案。動的領域のみのトークン更新と2ステップの拡散サンプリングにより、性能を保ちつつ2倍以上の高速化を達成。
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: Yuzhou Wu, Yuxin Zheng, Muchun Niu, Yishan Yang, Tianhao Liu, hanwen kang, Jiajian Jing, Linfeng Zhang, Chuan Wen
分類: cs.RO
原文アブストラクト
Vision-Language-Action (VLA) models exhibit strong generalization for robotic manipulation, yet their high inference latency limits real time deployment. We identify two primary sources of temporal redundancy in existing VLA pipelines: repeated visual encoding of highly similar consecutive frames and multi step iterative sampling in diffusion based policies. To address this, we propose a system level acceleration strategy that reduces computation in both perception and action generation. On the perception side, we incrementally update only tokens corresponding to dynamic scene regions instead of re-encoding entire frames. On the policy side, we compress diffusion sampling into a compact 2-step schedule through efficiency oriented training while preserving action precision. Experiments on Libero, RobotWin, and Real Robot Platforms demonstrate over 2 times speedup while maintaining high performance, achieving up to 98% success rate on general manipulation benchmarks. Our codes will be released on Github.
