Shengyang Sun

Shengyang Sun is a deep learning applied scientist at NVIDIA, focusing on improving large language model performances in the post-training process. His research involves model alignment algorithms, synthetic data generation, and reasoning. Prior to NVIDIA, Shengyang obtained his Ph.D. in computer science at the University of Toronto, focusing on scalable uncertainty estimation in deep neural networks.
Avatar photo

Posts by Shengyang Sun

Icon image of a chart and search symbol, on a purple background.
Generative AI Dec 17, 2024

Data-Efficient Knowledge Distillation for Supervised Fine-Tuning with NVIDIA NeMo-Aligner

Knowledge distillation is an approach for transferring the knowledge of a much larger teacher model to a smaller student model, ideally yielding a compact,... 5 MIN READ