Search papers, labs, and topics across Lattice.
2
0
4
4
Unified OCR foundation models achieve state-of-the-art visual intelligence by integrating recognition, parsing, and reasoning through instruction-following and a novel competence-guided policy optimization.
MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-Transformer backbone with optimized block structure and stacking scheme, achieves state-of-the-art performance on VoxCeleb1 and delivers strong results on CN-Celeb, demonstrating its effectiveness across diverse datasets.
