Search papers, labs, and topics across Lattice.
4
0
9
Real-world GUI agents can achieve over 72% success in complex mobile tasks by leveraging a unique hybrid training approach that integrates real-device execution and adaptive learning from failures.
Agents can now escape the Self-Confirmation Trap, leading to more reliable experience learning and improved self-evolution.
Dataset condensation, already vulnerable to backdoor attacks, now faces a far stealthier threat: InkDrop leverages decision boundary uncertainty to hide malicious triggers, making detection significantly harder.
By explicitly modeling tooth relationships, TCATSeg achieves state-of-the-art accuracy in 3D dental model segmentation, even in challenging pre-orthodontic cases.
