TempoFit: 長期的視覚言語行動操作のためのプラグアンドプレイ層別時間KVメモリ
TempoFit: Plug-and-Play Layer-Wise Temporal KV Memory for Long-Horizon Vision-Language-Action Manipulation
事前学習済みの視覚言語行動(VLA)ポリシーに、追加学習なしで時間的記憶を注入するTempoFitを提案。層ごとのKVキャッシュと再帰バイアスにより、長期的な操作タスクの成功率を向上させる。
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: Jun Sun, Boyu Yang, Jiahao Zhang, Ning Ma, Chencheng Wu, Siqing Zhang, Yiou Huang, Qiufeng Wang, Shan Liang, Yaran Chen
分類: cs.RO
原文アブストラクト
Pretrained Vision-Language-Action (VLA) policies have achieved strong single-step manipulation, but their inference remains largely memoryless, which is brittle in non-Markovian long-horizon settings with occlusion, state aliasing, and subtle post-action changes. Prior approaches inject history either by stacking frames, which scales visual tokens and latency while adding near-duplicate pixels, or by learning additional temporal interfaces that require (re-)training and may break the original single-frame inference graph. We present TempoFit, a training-free temporal retrofit that upgrades frozen VLAs through state-level memory. Our key insight is that prefix attention K/V already form a model-native, content-addressable runtime state; reusing them across timesteps introduces history without new tokens or trainable modules. TempoFit stores layer-wise FIFO prefix K/V at selected intermediate layers, performs parameter-free K-to-K retrieval with Frame-Gap Temporal Bias (FGTB), a fixed recency bias inspired by positional biases in NLP, to keep decisions present-dominant, and injects the retrieved context via pre-attention residual loading with norm-preserving rescaling to avoid distribution shift under frozen weights. On LIBERO-LONG, TempoFit improves strong pretrained backbones by up to +4.0% average success rate while maintaining near-real-time latency, and it transfers consistently to CALVIN and real-robot long-horizon tasks.
