I'm Yin Xie (yiyexy), a deep learning algorithm engineer specializing in computer vision, large-scale vision-language models, model compression & acceleration, and distributed training. My recent work focuses on visual representation learning, end-to-end facial feature pretraining, and pretraining techniques for vision-language models, with several papers published in top conferences and active contributions to open-source projects. Open to collaboration and discussion!😊
- Email : yiye.xieyin@gmail.com