ロックインの打破：低データVLA後訓練における操縦性の維持
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
低データでの後訓練後にVLAポリシーが新しい指示に応答しなくなる「ロックイン」現象を特定し、視覚的接地の維持とテスト時の対照的プロンプトガイダンスによりこれを緩和するDeLock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: Suning Huang, Jiaqi Shao, Ke Wang, Qianzhong Chen, Jiankai Sun, Yanjiang Guo, Mac Schwager, Jeannette Bohg
分類: cs.RO, cs.CV
原文アブストラクト
Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limited to behaviors observed during post-training? We identify this phenomenon as lock-in: after low-data, supervised fine-tuning (SFT), the policy becomes overly specialized to the post-training data and fails to generalize to novel instructions, manifesting as concept lock-in (fixation on training objects/attributes) and spatial lock-in (fixation on training spatial targets). Many existing remedies introduce additional supervision signals, such as those derived from foundation models or auxiliary objectives, or rely on augmented datasets to recover generalization. In this paper, we show that the policy's internal pre-trained knowledge is sufficient: DeLock mitigates lock-in by preserving visual grounding during post-training and applying test-time contrastive prompt guidance to steer the policy's denoising dynamics according to novel instructions. Across eight simulation and real-world evaluations, DeLock consistently outperforms strong baselines and matches or exceeds the performance of a state-of-the-art generalist policy post-trained with substantially more curated demonstrations.
