BLURR: 視覚言語行動モデルのための低リソース推論ブースト
BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
再学習なしで既存のVLAコントローラに組み込める軽量推論ラッパーBLURRを提案し、KVキャッシュや混合精度、単一ステップロールアウトで計算量と遅延を削減した。
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: Xiaoyu Ma, Zhengqing Yuan, Zheyuan Zhang, Kaiwen Shi, Lichao Sun, Yanfang Ye
分類: cs.RO
原文アブストラクト
Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot control on commodity GPUs. We present BLURR, a lightweight inference wrapper that can be plugged into existing VLA controllers without retraining or changing model checkpoints. Instantiated on the pi-zero VLA controller, BLURR keeps the original observation interfaces and accelerates control by combining an instruction prefix key value cache, mixed precision execution, and a single step rollout schedule that reduces per step computation. In our SimplerEnv based evaluation, BLURR maintains task success rates comparable to the original controller while significantly lowering effective FLOPs and wall clock latency. We also build an interactive web demo that allows users to switch between controllers and toggle inference options in real time while watching manipulation episodes. This highlights BLURR as a practical approach for deploying modern VLA policies under tight compute budgets.
