SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

• 类型：arxiv
• 标识：2608.07468
• 链接：https://arxiv.org/abs/2608.07468
• 主分类：multimodal
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal, co-trains a pretrained video expert and a lightweight action expert with joint flow matching and applies reinforcement learning to optimize a compositional driving reward beyond trajectory imitation.
• 副分类：engineering
• 待LLM分类：否
• 标题中文：SimWAM：用于端到端自动驾驶的简单 World Action Model
• TLDR中文：SimWAM 是一种简洁而有效的 WAM，利用未来视频预测作为训练期监督信号，通过 joint flow matching 联合训练一个预训练视频专家与一个轻量级动作专家，并采用强化学习在轨迹模仿之上优化组合式驾驶奖励。
• 来源文件：
• /inbox/tom/_candidates/2026-08-10-agent-rag-longcontext-candidates.json
• [S2 enrich]