Bin Liang

Large language models have improved dialogue systems, but often process conversational turns in isolation, overlooking the event structures that guide natural interactions. Hence we introduce EventWeave, a framework that explicitly models relationships between conversational events to generate mo...

Multimodal Stance Detection (MSD) is a crucial task for understanding public opinion on social media. Existing methods predominantly operate by learning to fuse modalities. They lack an explicit reasoning process to discern how inter-modal dynamics, such as irony or conflict, collectively shape t...

Large language models (LLMs) can call tools effectively, yet they remain brittle in multi-turn execution: after a tool-call error, smaller models often fall into repetitive invalid re-invocations instead of interpreting the feedback and recovering. This failure mode persists because current train...

Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. W...

While large language models (LLMs) have made significant progress in expanding their context windows, they still face great challenges in effectively organizing and utilizing long-term memory to maintain conversation consistency and coherence. Summarizing historical conversations has achieved rem...