Search papers, labs, and topics across Lattice.
5
0
9
4
Open-AoE transforms egocentric video capture into a powerful resource for embodied intelligence, making it easier than ever to train robots with human-like manipulation skills.
DT-Guard outperforms larger models in safety classification while maintaining low-latency performance, proving that reasoning supervision can be efficiently internalized.
Visual-Seeker outperforms proprietary models by actively engaging with visual details, redefining multimodal search capabilities.
SeClaw reveals that existing benchmarks fall short in capturing the complexities of agent behavior, enabling a more nuanced evaluation of security risks in autonomous systems.
By framing image manipulation localization as a courtroom trial between manipulated and authentic evidence, this work achieves state-of-the-art performance, even when manipulation traces are subtle.
