Search papers, labs, and topics across Lattice.
3
0
7
TwinIR can degrade HD map accuracy by nearly 9% while remaining nearly invisible to the human eye, posing a significant threat to autonomous driving safety.
LLMs can move beyond simply assisting static analysis to orchestrating it, enabling the discovery of critical zero-day vulnerabilities.
You can now fine-tune personalized diffusion models to generate avatars that are both high-fidelity and resistant to facial recognition, offering a tunable privacy-utility trade-off.
