Search papers, labs, and topics across Lattice.
University of North Carolina at Chapel Hill, University of Central Florida
2
0
4
HarnessRisk reveals that up to 80.9% of adversarial attacks can succeed in agent harnesses, even when risk detection is high.
Forget full intrinsic decomposition: LightCtrl achieves state-of-the-art single-image relighting by learning sparse, physically meaningful latent proxies from limited PBR data.
