DiMaS: 分布マッチングによる視覚言語行動モデルの制御
DiMaS: Distribution Matching for Steering Vision-Language-Action Models
フローマッチング型の視覚言語行動モデル(VLA)に対して、内部表現の分布を移動させることで行動を細かく制御する手法DiMaSを提案した。従来の線形ステアリングがVLAでは効果が薄いことを示し、分布マッチングが有効であることを実証した。
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: Pegah Khayatan, Sara Meziane, Jayneel Parekh, Matthieu Cord
分類: cs.RO, cs.LG
原文アブストラクト
Flow-matching-based vision-language-action (VLA) models have emerged as powerful policies for robotic manipulation, yet a critical capability remains underexplored: fine-grained behavioral control, the ability to govern how a robot performs a task by intervening on its internal representations. Representation steering is a well-established interpretability tool for language and vision-language models, where behavioral features are typically encoded as linear directions, but we show that these classic methods fall short in VLAs. We propose DiMaS, a Distribution-Matching Steering strategy tailored to flow-matching VLAs, which transports between representation distributions rather than shifting along a fixed direction, and show that it effectively controls behavior across two state-of-the-art VLAs. We further examine the generalizability of this strategy as the tasks it is learned from and evaluated on grow increasingly dissimilar, characterizing where behavioral control transfers and where it weakens. Finally, through an analysis of the representation structure of the action expert, we explain why classical linear steering falls short in the visuomotor setting: behavioral features are linearly decodable but not linearly steerable, which motivates the distribution-matching design of DiMaS. Our code is publicly available at https://github.com/pegah-kh/dimas, with additional results and videos at https://pegah-kh.github.io/dimas/
