Tagged with

2 articles found

Qwen-Drive-1.0: Alibaba Just Dropped an Open-Weight Model That Sees, Thinks, and Steers

Alibaba’s Qwen-Drive-1.0 unifies 3D perception, scene understanding, and motion planning in a single 9B model. Here’s what it actually does, and what it still can’t do.

#3D Perception#Autonomous Driving#Open Source AI...

document parsing

Chandra Just Made Every Other PDF Parser Look Like a Scanner from 1999

Datalab’s Chandra swept a 14-category PDF parsing benchmark with perfect scores. Here’s why that matters for RAG pipelines and why you should care about the speed tradeoff.

#document parsing#PDF parsing#vision-language models