Chi-Chih Chang

About me

I am a first-year Ph.D. student in the Computer System Laboratory at Cornell University, advised by Prof. Mohamed S. Abdelfattah. My research interests broadly encompass building machine learning systems and designing efficient algorithms for accelerating AI and ML applications.

Before joining Cornell, I completed my B.S. in Computer Science at National Yang Ming Chiao Tung University in Taiwan, where I worked with Prof. Kai-Chiang Wu. During my senior year, I was fortunate to gain research experience as a remote intern under the guidance of Prof. Luis Ceze at the University of Washington, mentored by Chien-Yu Lin. I also had the wonderful oppurtunities to collaborate with Prof. Diana Marculescu at UT Austin, which further strengthened my enthusiasm for tackling the inefficiency challenges in AI and ML applications, especially for LLM.

News

Nov 01, 2024	I am seeking a research scientist internship position for the summer of 2025. Topics: Efficient Machine Learning Algorithm, Machine Learning System.
Aug 26, 2024	I’ve started my PhD in Cornell University! Excited for this new chapter in my academic journey.

Selected publications

Palu: Compressing KV-Cache with Low-Rank Projection

Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin, Chong-Yan Chen, Yu-Fang Hu, and 4 more authors

arXiv preprint arXiv:2407.21118, 2024

Bib PDF

@article{chang2024palu,
  title = {Palu: Compressing KV-Cache with Low-Rank Projection},
  author = {Chang, Chi-Chih and Lin, Wei-Cheng and Lin, Chien-Yu and Chen, Chong-Yan and Hu, Yu-Fang and Wang, Pei-Shuo and Huang, Ning-Chi and Ceze, Luis and Wu, Kai-Chiang},
  journal = {arXiv preprint arXiv:2407.21118},
  year = {2024},
  venue_type = {arXiv},
  venue_url = {https://arxiv.org/abs/2407.21118},
}

Quamba: A Post-Training Quantization Recipe for Selective State Space Models

Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, and Diana Marculescu

arXiv preprint arXiv:2410.13229, 2024

Bib PDF Website

@article{chiang2024quamba,
  title = {Quamba: A Post-Training Quantization Recipe for Selective State Space Models},
  author = {Chiang, Hung-Yueh and Chang, Chi-Chih and Frumkin, Natalia and Wu, Kai-Chiang and Marculescu, Diana},
  journal = {arXiv preprint arXiv:2410.13229},
  year = {2024},
  url = {https://arxiv.org/abs/2410.13229},
  venue_type = {arXiv},
  venue_url = {https://arxiv.org/abs/2410.13229},
  publisher = {arXiv}
}

FLORA: Fine-Grained Low-Rank Architecture Search for Vision Transformer

Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu, Ning-Chi Huang, Diana Marculescu, and 1 more author

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024

Bib PDF

@inproceedings{Chang_2024_WACV,
  author = {Chang, Chi-Chih and Sung, Yuan-Yao and Yu, Shixing and Huang, Ning-Chi and Marculescu, Diana and Wu, Kai-Chiang},
  title = {FLORA: Fine-Grained Low-Rank Architecture Search for Vision Transformer},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  month = jan,
  year = {2024},
  pages = {2482-2491},
}