VISTA: 視覚条件付けを強化する追従選好最適化によるVLAモデル
VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models
VLAモデルが視覚状態に弱く依存してしまう問題に対し、追従タスクでの選好最適化と潜在蒸留で視覚条件付けを強化し、タスク性能を向上させた。
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: Yiye Chen, Yanan Jian, Xiaoyi Dong, Shuxin Cao, Jing Wu, Patricio Vela, Benjamin E. Lundell, Dongdong Chen
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
Vision-Language-Action (VLA) models have demonstrated strong performance across a wide range of robotic manipulation tasks. Despite the success, extending large pretrained Vision-Language Models (VLMs) to the action space can induce vision-action misalignment, where action predictions exhibit weak dependence on the current visual state, leading to unreliable action outputs. In this work, we study VLA models through the lens of visual conditioning and empirically show that successful rollouts consistently exhibit stronger visual dependence than failed ones. Motivated by this observation, we propose a training framework that explicitly strengthens visual conditioning in VLA models. Our approach first aligns action prediction with visual input via preference optimization on a track-following surrogate task, and then transfers the enhanced alignment to instruction-following task through latent-space distillation during supervised finetuning. Without introducing architectural modifications or additional data collection, our method improves both visual conditioning and task performance for discrete OpenVLA, and further yields consistent gains when extended to the continuous OpenVLA-OFT setting. Project website: https://vista-vla.github.io/ .
