1
OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation
多智能体世界模型结合LLM，统一潜在共压缩实现多视角驾驶视频生成，创新突破自动驾驶领域
arXiv:2606.17536v1 Announce Type: cross Abstract: Generative world models for autonomous driving face two unresolved tensions: heterogeneous control i…