Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
14
A 202-scenario benchmark with Reference Decisions under a seven-class taxonomy is introduced and Decision Alignment and safety-specific error metrics are evaluated, finding structured LLM decisions are insufficient as a standalone safety mechanism and deployment requires an independent enforcement layer.
A novel balanced soft mixture-of-expert model achieves unprecedented accuracy in glaucoma detection, outpacing existing multi-modal and uni-modal approaches.
Achieving 98.89% accuracy in reconstructing G-code commands from a non-line-of-sight attack using just two smartphones reveals alarming vulnerabilities in additive manufacturing security.
