GREx: Why “All People” Breaks Every Referring Expression Model — And What NTU Did About It | AI Trend Blend Vision-Language · Segmentation GREx: Why “All People” Breaks Every Referring Expression Model — And What These Researchers Did About It A team from NTU and Fudan University identified a blind spot that has haunted referring […]
PRECTR-V2: How Alibaba Solved Cold-Start, Exposure Bias, and Frozen Encoders in One Unified Search Ranking Framework | AI Trend Blend AITrendBlend Machine Learning About Recommendation Systems · arXiv:2602.20676 · Alibaba Group / Xianyu · 18 min read PRECTR-V2: How Alibaba Solved Cold-Start, Exposure Bias, and a Frozen Encoder — All in One Unified Search Ranking
Introduction: Why Out-of-Scope Detection Matters in Dialog Systems In the rapidly evolving world of artificial intelligence, dialog systems have become a cornerstone of modern customer service, virtual assistants, and chatbots. These systems rely heavily on intent classification to understand and respond to user queries. However, one of the most significant challenges they face is out-of-scope
