kun wang
4
Papers
46
Total Citations
Papers (4)
On the Role of Attention Heads in Large Language Model Safety
ICLR 2025arXiv
40
citations
Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
NeurIPS 2025arXiv
4
citations
Multi-scale Cross Distillation for Object Detection in Aerial Images
ECCV 2024
2
citations
Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
NeurIPS 2025arXiv
0
citations