Neng Zhang — accepted AI-conference papers

2026

Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving

Zehan Zhang, Yaoyi Li, Neng Zhang, Jia Cai

CVPR 2026

Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop driving. Several methods attempt to inject history as a static conditioning sign

Cited by 0 Source ↗Scholar ↗

2026

WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving

Yifang Xu, Jiahao Cui, Zhihao Zhu, Hanlin Shang, Shan Luan, Mingwang Xu +5

CVPR 2026

We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressive decoders, WAM-Flow performs fully parallel, bidirectional denoising, enabling coarse-to-fine refinement with a tunable

Cited by 0 Source ↗code ↗Scholar ↗