2 papers
cs.CL2026
Search-R3: Unifying Reasoning and Embedding in Large Language Models
Yuntao Gui, James Cheng
Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framew…
cs.DC2025
PilotANN: Memory-Bounded GPU Acceleration for Vector Search
Yuntao Gui, Peiqi Yin, Xiao Yan +3
Approximate Nearest Neighbor Search (ANNS) has become fundamental to modern deep learning applications, having gained particular prominence through its integration into recent gene…