提出一种高效车载世界模型状态流传输方法，降低带宽消耗并提升预测性能。
Network-Efficient World Model Token Streaming
- 用余弦距离动态优先更新，自适应触发关键帧，减少冗余数据传输。
- 在200字节/帧预算下，动态状态失真降低7.2%，预测困惑度下降6.3%。
- 适用于车联网络环境，兼顾带宽限制与下游任务实用性，适合自动驾驶系统部署。
生成式自动驾驶世界模型依赖紧凑的隐状态表示，需在分布式计算与联网车辆间高效传输和同步。本文研究离散世界模型状态的网络高效流传输，采用步长为16的VQ-U-Net分词器（码本大小8,192），将每帧288x512图像映射为18x32的令牌网格（576个令牌/帧），固定编码下相当于936字节/帧。在严格单消息负载与丢包条件下，提出全在线、无标签的键帧-增量协议：通过码本嵌入空间中的余弦距离优先处理增量更新，并基于汉明漂移阈值自适应触发关键帧。该自适应算法在相同比特率下持续优于周期性关键帧：在0.024 Mb/s（200字节预算）时，动态嵌入失真由0.0712降至0.0661（降幅7.2%）；在0.036 Mb/s（400字节）时由0.0427降至0.0407（降幅4.8%）。在10%增量包丢失下，200字节时动态失真为0.0757，优于匹配周期基线的0.0789。为连接状态保真度与世界模型实用性，训练轻量级下一令牌预测器，评估接收端状态条件下的困惑度：在0.024 Mb/s时，动态位置困惑度从206.0降至193.1（降幅6.3%）；在0.036 Mb/s时从158.9降至155.6（降幅2.1%）。结果表明，离散令牌状态流是一种面向带宽敏感场景的实用系统层方案，可实现车辆网络约束下的高效同步与下游令牌动态利用。
原文摘要 · Abstract (English)
Generative driving world models rely on compact latent state representations that must be efficiently transmitted and synchronized across distributed compute and connected vehicles. We study network-efficient streaming of a discrete world model state, where a stride-16 VQ-U-Net tokenizer (codebook size 8,192) maps each 288x512 frame to an 18x32 grid of token IDs (576 tokens/frame), equivalent to 936 bytes/frame under fixed-length coding. We consider a keyframe--delta protocol under strict per-message payload budgets and packet loss, and propose a fully online, label-free algorithm that prioritizes delta updates via cosine distance in codebook embedding space and triggers keyframes adaptively using a Hamming-drift threshold. The adaptive algorithm consistently improves the rate distortion frontier over periodic keyframes at matched bitrates: at 0.024 Mb/s (200-byte budget) dynamic-only embedding distortion drops from 0.0712 to 0.0661 (7.2\%), and at 0.036 Mb/s (400-byte budget) from 0.0427 to 0.0407 (4.8\%). Under 10\% delta packet loss at 200 bytes, dynamic-only distortion is 0.0757 versus 0.0789 for a matched periodic baseline. To connect state fidelity to world model usefulness, we train a lightweight next-token predictor and evaluate perplexity conditioned on streamed receiver states: at 0.024 Mb/s, dynamic-position perplexity improves from 206.0 to 193.1 (6.3\%), and at 0.036 Mb/s from 158.9 to 155.6 (2.1\%). These results support discrete token-state streaming as a practical systems layer for bandwidth-aware synchronization and improved downstream token-dynamics utility under vehicular networking constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。