Tri-Info: 情報理論によるVLAモデルの汎用的で解釈可能な失敗予測
Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
VLAモデルの動作を情報理論の観点から分析し、成功と失敗で異なる情報的シグネチャを捉えるTri-Info信号を提案。再学習なしでアーキテクチャや環境をまたいで失敗を検出でき、実世界タスクでも高い精度を達成。
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: Jinghan Yang, Yunchao Zhang, Wang Yuan, Haolun Wan, Jiaming Zhang, Zhengyang Hu, Yanchao Yang
分類: cs.RO, cs.AI, cs.CV, cs.LG
原文アブストラクト
Vision-Language-Action (VLA) models are increasingly deployed across diverse tasks, yet they remain black boxes whose physical interactions can cause irreversible harm, making generalizable and interpretable failure detection essential. We observe that successful and failed rollouts carry systematically different information-theoretic signatures. Building on this, we formalize VLA control as a closed-loop information pipeline and derive the Triple Information-theoretic (Tri-Info) signals that capture whether actions remain diverse, temporally consistent, and coupled to state transitions. Across six VLA models and three benchmark environments, Tri-Info matches the strongest baselines in-domain. Moreover, Tri-Info transfers across architectures, environments, and the sim-to-real gap without retraining, reaching 83\% accuracy on real-world tasks where prior detectors collapse to chance. This establishes Tri-Info as a simple yet powerful method that not only detects failures with strong cross-domain generalization, but also delivers interpretable diagnostics of the underlying failure modes.
