Jiangmiao Pang

CLIP exhibits strength in handling data imbalance in visual and language tasks.

MMScan enhances AI’s ability to comprehend complex 3D environments with extensive annotations.

A new method aids robots in carrying objects collaboratively.

OVExp combines language and vision for effective object navigation in varied environments.

LLaVA-3D combines 2D and 3D insights for deeper spatial reasoning.

A new model helps robots blend vision with action for improved manipulation skills.