2 papers
cs.IR2026
Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale
Hao Fu, Jichao Sun, Baiting Zhu +15
Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, expressive personalization for que…
cs.IR2026
Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale
Hao Fu, Baiting Zhu, Minglei Chen +2
Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a self-cont…