前沿 | VLA 演进:从动作 Token 到分层具身智能体论文:Zitkovich et al., RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control, CoRL 2023。 论文:Black et al., π₀: A Vision-Language-Action Flow Model for General Robot Control, RSS 2025。 论文:Pertsch et al., FAST: Efficient Action Tokeniza