Search papers, labs, and topics across Lattice.
6
0
8
3
Test-time scaling allows UAV navigation VLMs to self-correct and achieve state-of-the-art performance without any additional training.
VLMs struggle with raw medical data, achieving only a 48.6% success rate in standardization, revealing a critical gap in their clinical applicability.
Personalizing mobile GUI agents for privacy requires navigating structurally different execution trajectories, and TIPO offers a way to do it.
Radiology data can be de-identified for cross-hospital sharing without sacrificing diagnostic utility, unlocking larger and more diverse training datasets for medical AI.
Get more from less: SonoSelect intelligently guides ultrasound probes to achieve comparable diagnostic accuracy with far fewer views, slashing scanning time and processing costs.
The medical imaging AI community is being held back by a fragmented data landscape, but a new metadata-driven fusion paradigm offers a path to unlocking the power of foundation models.
