Search papers, labs, and topics across Lattice.
Dalian University of Technology
7
0
7
Text safety neurons in VLMs are localized and critical, while visual safety mechanisms are diffuse and complex, revealing a fundamental gap in current alignment strategies.
Achieving 94.36% accuracy in gesture recognition with a lightweight model opens new avenues for intuitive human-machine interfaces on portable devices.
Uncertainty-aware segmentation can drastically improve performance in medical imaging, with DistMedVL achieving superior results using only 6.3M parameters.
A robotic craniotomy system that autonomously adapts to unknown tissue properties, achieving high precision in temperature estimation and surgical execution.
Achieving a 90% reduction in data volume without sacrificing accuracy, this integrated optoelectronic architecture revolutionizes robotic visual inspection.
Forget relying on fickle visuals: this new ReID method uses language to describe *who* a person is, not just what they look like, and it crushes existing benchmarks.
Stop reacting to unsafe LLM outputs and start predicting them: StreamGuard forecasts the harmfulness of future text, enabling earlier and more effective safety interventions.
