Anh Nguyen

Overcoming the quadratic complexity of historical context integration, DCA achieves significant efficiency gains while enhancing performance in Vision-Language Models.

Sparse contact masks can reduce redundant data and accelerate human-scene interaction models by over 12 times while boosting accuracy.

Surgeons can now access real-time insights from surgical videos with over 100x faster response times, thanks to a novel generative retrieval framework.

A single click can now inform the segmentation of multiple objects in remote sensing images, drastically cutting down the annotation effort required.

Current robotic grasping methods struggle, with success rates under 70% in complex scenarios that demand reasoning and semantic understanding.