推論コストなしの推論:ロボットVLAポリシーのための潜在意味的足場
Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies
ロボットのVLAモデルに、推論時のコストを増やさずに物理的推論の能力を持たせるため、訓練中にアクショントークンの表現をテキストの推論根拠に合わせる補助損失を導入し、推論時にはそのヘッドを捨てる手法を提案した。
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: Andrew Ting Yan Li, Zhuo Li, Zhelin Yang, Zhipeng Dong, Quentin Rouxel, Fei Chen
分類: cs.RO
原文アブストラクト
Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation, but current methods pay for it at inference time - generating reasoning tokens or rolling out predicted future states at every step, a cost that compounds over long horizons. We ask whether this benefit can instead be captured during training and discarded before deployment. We introduce Latent Semantic Scaffolding (LSS), an auxiliary loss applied during human-demonstration pretraining that aligns a VLA's action-token representations to text embeddings of physical-reasoning rationales through a small projection head. The head is dropped at inference, leaving the unmodified base policy with zero added cost. Our central finding concerns alignment granularity: aligning each action token to the rationale of its own manipulation phase (Dense LSS) rather than to a single pooled episode-level embedding (Pooled LSS) yields representations that transfer markedly better to held-out tasks. Dense LSS attains both the best in-distribution success and the best transfer to tasks unseen during alignment, whereas pooled alignment over-specializes to the training task. A representational probe shows Dense LSS induces roughly twice the per-phase separability in the backbone, supporting that phase-local alignment is the operative mechanism.