再構築の迷子:視覚-言語-行動モデルにおける行動表現と言語の整合
Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models
行動軌跡には言語的意味情報が含まれるが、再構築のみのトークン化で失われるため、凍結VLMで指示を復元する補助損失を持つセマンティック整合トークナイザSALTを提案し、言語条件付き制御の成功率を大幅に向上させた。
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: Li Wenjie, Yash Jangir, Ignacy Stepka, Yash Agarwal, Marion Kipsang, Yonatan Bisk
分類: cs.RO, cs.AI, cs.CL
原文アブストラクト
Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-language-action models (VLAs) are typically optimized for reconstruction under L1/L2 losses in raw action space, where numerical proximity need not reflect linguistically meaningful distinctions. On BridgeV2, we show that action trajectories contain verb-grounding information beyond visual state changes, and that reconstruction-only discrete tokenization systematically erodes this information. To address this problem, we introduce SALT, a Semantically ALigned action Tokenizer that augments a VQ-VAE-style tokenizer with an auxiliary objective requiring a frozen vision-language model to recover the episode instruction from quantized action latents. Policies trained with SALT achieve 71.9% average success in SimplerEnv, compared with 42.7% for a reconstruction-only VQ-VAE tokenizer and 31.2% for FAST. SALT also develops verb-specialized codes while maintaining reconstruction fidelity. These results show that robot action trajectories provide a source of language grounding and that preserving this structure in action representations can substantially improve language-conditioned control.