Jiaqi Wu

Revisiting CNN-based multi-resolution modeling for long-term time series forecasting

Positive-Unlabeled Learning for Agent Safety False Alarm Auditing

Safety monitors help safeguard language-model agents interacting with external tools and environments, but conservative monitoring can generate many false alarms, consuming extensive review resources and weakening trust in alerts. Because false and genuine alarms often remain interleaved in native monitor scores, obtai...

From Relevance to Utility: Faith-Rank for Utility-Driven Evidence Re-ranking and Reliable Answering in Retrieval-Augmented Generation