Yingli Tian

AMRD achieves superior performance in speech emotion recognition by leveraging the strengths of multiple teachers while capturing relational structures that traditional methods miss.

Robot video world models can be significantly improved by distilling a multimodal reward function and stabilizing long-horizon inference, leading to better instruction following and manipulation accuracy.

A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.