VLM

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory …
PDF Cite Code Project
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally …
PDF Cite Code Project
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM