Jun-Hui Li

This work augments the LALM with a dedicated frame-level grounding model while leveraging its semantic modeling capability to represent the event query, and shows that the grounding model can provide temporal evidence to support downstream reasoning.

Compact models can now outperform massive systems like GPT-4o in document translation by leveraging a new metric that prioritizes structural fidelity.

Emotion-driven feedback can transform multi-turn dialogue systems, boosting empathetic responses and model performance significantly.

Nearly 20% of LLM agent violations occur even after agents acknowledge safety constraints, highlighting a critical gap in execution awareness.

U$^2$Mamba achieves superior salient object detection by integrating contextual information across multiple layers without sacrificing resolution.

Teaching emotional support chatbots specific, executable skills, rather than relying on end-to-end training, leads to more interpretable, controllable, and ultimately more helpful conversations.

Allowing multiple support strategies in a single utterance can dramatically enhance the quality of emotional support conversations, leading to more effective dialogue outcomes.