Qi Chen

VisionCreator, an 8B/32B agent, beats larger closed-source models at visual content creation by unifying understanding, thinking, planning, and creation within a single end-to-end framework.

Unlock compositional reasoning in 3D vision-language models with a new dataset that maps noun phrases to 3D instances, revealing improvements on both fine-grained and traditional segmentation tasks.

Stop crippling your GPU scans: CPU-centric Parquet defaults are likely the culprit, not the format itself.