Yuming Lou

About Me

I am a passionate PhD student at Princeton CS, advised by Professor Kai Li and Professor Ravi Netravali. Before that, I did my undergraduate at EE, Tsinghua University. My work focuses on efficient AI, ranging from algorithm to system.

In the past, I am honored to work under the supervision of Professor Yu Wang and Xuefei Ning at Tsinghua to explore quantization algorithm.

I am also honored to work as an intern at MIT HAN Lab, under the supervision of Professor Song Han, Shang Yang and Haotian Tang to explore efficient system designing for quantized LLMs.

I also collaborated closely with Jason Lu from Nvidia Research.

Projects

• Project 1 - I contribute intensively and co-led TinyChat 2.0.

Publications

• Liu, Z., Zhu, L., Shi, B., Zhang, Z., Lou Y., et al. (2024). NVILA: Efficient Frontier Visual Language Models.
• Yang, S., Lou Y., Guo, J., Tang, J., Tang, H., & Han, S. (2024). TinyChat 2.0: Accelerating Edge AI with Efficient LLM and VLM Deployment. MIT Han Lab.
• Zhou, Z., Ning, X., Hong, K., Fu, T., Xu, J., Li, S., Lou Y., et al. (2024). A Survey on Efficient Inference for Large Language Models.

Interests

• I enjoy a variety of sports, from badminton to basketball.
• I'm also passionate about movies and TV series.

Contact

Feel free to reach out to me through my email.