Hugging Face Trending Papers

FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving

Read the original on Hugging Face Trending Papers →

Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade of four.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
1d ago

Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures

arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.

By Haibo HU, Lianming Huang, Qiao Li, Nan Guan, Chun Jason Xue
arXiv AI
Aug 10

WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA

arXiv:2608. 01035v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.

By Zhihao Zhu, Hanlin Shang, Mingwang Xu, Feipeng Cai, Zhuolin He, Yaoyi Li, Jianhua Han, Hang Xu, Siyu Zhu