Search papers, labs, and topics across Lattice.
Affiliation:
5
0
7
0
Cross-attentive MLLMs already solve the attribute-binding failures that cripple embedding models鈥攁nd distilling their soft multi-level ranking distributions via Rank-KL unlocks that reasoning for bi-encoders without degrading standard recall.
DEPT achieves superior retrieval quality by preserving document embeddings while adapting query expansions, revealing a new synergy between these traditionally separate tasks.
Agents can significantly enhance retrieval performance in visually rich document environments, achieving a 67.50% Recall@1 compared to just 37.50% for OCR-text methods.
UEmbed achieves a groundbreaking unification of dense and sparse embeddings, outperforming existing models in multimodal tasks while streamlining the retrieval process.
Traditional code retrieval methods falter in agentic coding, but CORE-Bench reveals that fine-tuning can bridge the gap and boost performance significantly.
