Yuyang Wang

JFRDet achieves state-of-the-art performance in visible-infrared object detection by explicitly addressing severe geometric misalignment and illumination variability.

Multi-turn interactions can be effectively optimized in LLMs using tailored RL strategies, overcoming significant challenges in credit assignment and reward design.

BioKD achieves a remarkable 68.01% accuracy in trial-wise arousal recognition, showcasing the power of reliability-aware knowledge distillation in emotion recognition tasks.

Systematic feature engineering can outperform advanced model architectures, closing a critical evaluation gap in tabular benchmarks.

Forget complex updates: the secret to better molecular property prediction in MPNNs lies in how you initialize and fuse messages.