Search papers, labs, and topics across Lattice.
6
0
7
CoTIR achieves superior image restoration by internalizing reasoning processes, outperforming traditional methods even in complex degradation settings.
Achieve SOTA 3D scene reconstruction from collaborative driving views without calibration by treating multiple vehicles as a single, unstructured multi-camera system.
Finally, a way to train LLM agents to reason step-by-step without needing humans to check every intermediate thought.
Visual RL agents can recover near-perfect performance even under severe, dynamically changing visual corruptions by learning to disentangle task-relevant foreground from perturbation artifacts.
By cleverly embedding the face itself as a watermark within the background, RecoverMark offers a surprisingly robust defense against face manipulation, even when attackers try to remove the watermark.
A novel adversarial attack, MVIG, can reduce the success rate of state-of-the-art defenses in collaborative perception systems by up to 62%, revealing critical security gaps.
