Search papers, labs, and topics across Lattice.
University of Science
2
0
3
2
VietFashion reveals that current AI models struggle to capture the intricate cultural semantics of traditional garments, exposing significant gaps in fine-grained retrieval capabilities.
EVENT-Retriever demonstrates that combining language-based reasoning with multimodal retrieval significantly improves performance in complex, real-world image understanding tasks, achieving top-1 score in the EVENTA 2025 Grand Challenge.
