Search papers, labs, and topics across Lattice.
Beihang University
2
0
3
7
DEPT achieves superior retrieval quality by preserving document embeddings while adapting query expansions, revealing a new synergy between these traditionally separate tasks.
UEmbed achieves a groundbreaking unification of dense and sparse embeddings, outperforming existing models in multimodal tasks while streamlining the retrieval process.
