Search papers, labs, and topics across Lattice.
4
0
6
3
Recursive self-improvement in Macaron-V1 leads to continual learning that adapts to real-world experiences, setting a new standard for open agent models.
GeoMAR achieves superior face restoration by leveraging geometrically aligned features, outperforming traditional methods even under severe degradation.
VARPose achieves superior 2D pose densification, leading to enhanced performance in 3D lifting tasks, while generalizing to previously unseen pose granularities.
Cut your 3D-QA model's token budget by 91% and latency by 86% with a new pruning method that intelligently balances semantic importance and geometric coverage.
