CVPR Findings2026
See Tomorrow, Act Today: Foresight-Driven Autonomous Driving
Bozhou Zhang, Nan Song, Yuang Wang, Jiankang Deng, Xiatian Zhu, Li Zhang
Abstract
Current end-to-end autonomous driving planners are fundamentally reactive: they condition on historical and present observations to predict future actions. We argue that autonomous agents should instead imagine future scenes before deciding, just as human drivers mentally simulate "what will happen next" before acting. We introduce ForeSight, a foundation world model centric planning framework that reframes autonomous driving as anticipatory decision-making. Rather than treating world models as auxiliary components, ForeSight makes future scene imagination the primary driver of action prediction. Our approach operates in two stages: (1) generating plausible future visual worlds via a pretrained world model, and (2) planning actions conditioned on these imagined futures. This paradigm shift from "what should I do now?" to "what will happen, and how should I respond?" enables genuinely anticipatory rather than reactive planning. By grounding decisions in anticipated contexts rather than present observations alone, ForeSight navigates dynamic, interactive scenarios more effectively. Extensive experiments on NAVSIM and nuScenes demonstrate that explicit future imagination significantly outperforms previous stateof-the-art alternatives, validating our foresight-driven approach.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning cites VAD: Vectorized Scene Representation for Efficient Autonomous Driving
- Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability cites VAD: Vectorized Scene Representation for Efficient Autonomous Driving
- FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving cites VAD: Vectorized Scene Representation for Efficient Autonomous Driving
- FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving cites Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
Builds on46
- VAD: Vectorized Scene Representation for Efficient Autonomous DrivingBo Jiang, Shaoyu Chen, Qing Xu, Bencheng Liao et al.ICCV 2023 · 602 citations
- Vista: A Generalizable Driving World Model with High Fidelity and Versatile ControllabilityShenyuan Gao, Jiazhi Yang, Li Chen, Kashyap Chitta et al.NeurIPS 2024 · 403 citations
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-TuningZewei Zhou, Tianhui Cai, Seth Z. Zhao, Yun Zhang et al.NeurIPS 2025 · 310 citations
- MagicDrive: Street View Generation with Diverse 3D Geometry ControlRuiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong et al.ICLR 2024 · 248 citations
- FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous DrivingShuang Zeng, Xinyuan Chang, Mengwei Xie, Xinran Liu et al.NeurIPS 2025 · 228 citations
Related papers
- World4Drive: End-to-End Autonomous Driving via Intention-Aware Physical Latent World ModelYupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang et al.ICCV 2025 · 16 citations
- Learning Vision-Language-Action World Models for Autonomous DrivingGuoqing Wang, Pin Tang, Xiangxuan Ren, Guodongfang Zhao, Bailan Feng, Chao MaCVPR Findings 2026
- DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous DrivingFeiyang Jia, Lin Liu, Ziying Song, Caiyan Jia et al.ICML 2026 · 20 citations
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous DrivingYu Yang, Jianbiao Mei, Yukai Ma, Siliang Du et al.AAAI 2025 · 53 citations
- From Forecasting to Planning: Policy World Model for Collaborative State-Action PredictionZhida Zhao, Talas Fu, Yifan Wang, Lijun Wang et al.NeurIPS 2025 · 36 citations
