Heng Chang

PrimeSeeker: Capability-Oriented Supervision for Deep Search Agents

Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional hops, and longer trajectories. These global properties, however, are only indirect proxies for the local retrieval capabilities required during search. To address this m...

Cross-Domain Interest Representation Learning for Scenario- and Task-Aware Recommendation

Following the modular decomposition of industrial recommenders, STAR-CDR introduces three innovations: a CDI Extractor that enhances sequential modeling with domain indicators and other key features, and a CDI Injector that recalibrates activations and enables domain-/scenario-/task-aware expert routing.

Prompt and sequential selection transfer based large language model for traffic prediction with limited data