Dong Xu

LLMs can now generate more complete and up-to-date code documentation 3x faster while using 85% fewer tokens, thanks to a novel knowledge graph representation of code repositories.

Stop blind drawing: giving MLLMs eyes to see their work-in-progress boosts SVG generation performance.

Unlock previously inaccessible 3D microvascular insights from 2D ultrasound images with MVis-Fold, enabling more accurate disease diagnosis and monitoring.

Robots can now adapt to dynamic environments with minimal human involvement by learning from a world model and force-torque feedback, achieving state-of-the-art manipulation performance.