表現アンカリングと言語-行動整合による汎化可能なVLAファインチューニング
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
事前学習済みVLMをロボットデモでファインチューニングする際に生じる表現劣化と言語-行動の不整合を防ぐため、凍結VLMからの層別蒸留と行動を離散方向ラベル化して同一観測で言語・行動を学習する手法を提案し、実機とシミュレーションで性能向上を確認した。
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: Dwip Dalal, Shivansh Patel, Chahit Jain, Jeonghwan Kim, Utkarsh Mishra, Alex Baratian, Hyeonjeong Ha, Heng Ji, Svetlana Lazebnik, Unnat Jain
分類: cs.RO, cs.CV
原文アブストラクト
Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on web image-text data, a common remedy, does not prevent this; it applies language and action losses to separate observations, leaving VLAs with language-action misalignment that standard manipulation benchmarks do not expose. We propose Anchor-Align, which augments BC with two objectives: Vision-Language Anchoring distills layer-wise representations from a frozen VLM copy to prevent this drift, while Language-Action Alignment converts each action target into a discrete motion-direction label and jointly trains language and action prediction on the same robot observation. On a physical xArm7 robot, across two widely used VLA architectures, Anchor-Align improves real-robot success on both (28% to 54% and 37% to 60%). At scale in simulation, we demonstrate consistent improvements on OOD perturbations, perceptual robustness, and long-horizon control across LIBERO-PRO, LIBERO-Plus, and CALVIN, respectively, suggesting that preserving pretrained representations and effective action learning are not fundamentally at odds. Project page: anchoralignvla.github.io
