WAM-Diff2：蒸馏自回归 VLA 为扩散策略提速 WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA

精读摘要

视觉-语言-动作（VLA）模型是端到端自动驾驶的主流范式，但顺序自回归解码带来高计算延迟和暴露偏差，限制了高效部署。扩散策略虽能低延迟并行执行，从零训练却往往得到窄域的单任务架构，缺乏整体视觉-语言推理能力。WAM-Diff2 用分层蒸馏把预训练的自回归 VLA 迁移为扩散策略，兼顾通用推理与实时效率，为自动驾驶 VLA 落地提供了新路线。 VLA models are the leading paradigm for end-to-end autonomous driving, but sequential autoregressive decoding imposes high latency and exposure bias. Diffusion policies enable low-latency parallel execution, yet training them from scratch yields narrow single-task architectures. WAM-Diff2 uses hierarchical AR-to-diffusion distillation to transfer pretrained autoregressive generalists into efficient diffusion policies.