© Song Bian | Last updated: Feb 2026
Song BianGoogle Scholar |
I am a Research Scientist at NVIDIA Research working with Prof. Song Han.
I earned my PhD at the University of Wisconsin-Madison, advised by Prof. Shivaram Venkataraman. I completed my M.Phil. at The Chinese University of Hong Kong, advised by Prof. Jeffrey Xu Yu, and my B.S. at Zhejiang University, advised by Prof. Yunjun Gao.
My research interests lies in Large Language Models and Machine Learning Systems.
| Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs Song Bian, Tao Yu, Shivaram Venkataraman, Youngsuk Park The International Conference on Learning Representations, (ICLR), 2026. [paper] |
| Scaling Inference-Efficient Language Models Song Bian*, Minghao Yan*, Shivaram Venkataraman International Conference on Machine Learning, (ICML), 2025. [paper][code][model] |
| Does Compressing Activations Help Model Parallel Training? Song Bian*, Dacheng Li*, Hongyi Wang, Eric P. Xing, Shivaram Venkataraman Proceedings of Machine Learning and Systems (MLSys), 2024. [paper][code] |