Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving Paper • 2605.23163 • Published May 25 • 17
Efficient Training on Multiple Consumer GPUs with RoundPipe Paper • 2604.27085 • Published Apr 29 • 47
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 53