WAM-Diff

Papers using or citing this model 1

• WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving 10 citations · 2025 · arXiv (Cornell University) · arXiv

  End-to-end autonomous driving systems based on vision-language-action (VLA) models integrate multimodal sensor inputs and language instructions to generate planning and control signals. While autoregressive large language models and...