Jian Yu

Large language models (LLMs) enable zero-shot and few-shot multi-label text classification via in-context learning, yet most approaches perform static inference and degrade under streaming test data due to distribution shift and long-tail labels. We study online test-time adaptation for LLM-based...

Zero-shot Relational Learning (ZRL) aims to perform knowledge graph completion when dealing with newly emerging relations without instances of them. However, existing ZRL methods typically depend on external knowledge beyond Knowledge Graphs (KGs), resulting in increased annotation costs and limi...

Omni-modal Large Language Models (OLLMs) excel in diverse tasks but struggle with complex emotional reasoning, which requires integrating textual, visual, and acoustic signals. We attribute this limitation to modality collapse, where models over-rely on a dominant modality while neglecting comple...

Existing psychological counseling datasets often suffer from monolithic client personas, insufficient therapeutic depth, and a lack of process controllability. To address these critical limitations, we propose PsyChain , a chain-of-agents framework that evolves static counseling corpora into high...