Publications

2025

1. 

   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

   In Proceedings of International Conference on Learning Representations (ICLR), Apr 2025

   Bib PDF

   @inproceedings{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},
     booktitle = {Proceedings of International Conference on Learning Representations (ICLR)},
     year = {2025},
     month = apr,
   }

2. 

   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

   In Proceedings of International Conference on Learning Representations (ICLR), Apr 2025

   Bib PDF Website

   @inproceedings{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},
     booktitle = {Proceedings of International Conference on Learning Representations (ICLR)},
     year = {2025},
     url = {https://arxiv.org/abs/2410.13229},
   }

2024

1. 

   ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration

   Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2024

   Bib PDF

   @inproceedings{Huang_2024_CVPR,
     author = {Huang, Ning-Chi and Chang, Chi-Chih and Lin, Wei-Cheng and Taka, Endri and Marculescu, Diana and Wu, Kai-Chiang},
     title = {ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
     month = jun,
     year = {2024},
     pages = {8006-8015},
   }

2. 

   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},
   }

3. 

   Transformer and Its Variants for Identifying Good Dice in Bad Neighborhoods

   Cheng-Che Lu, Chi-Chih Chang, Chia-Heng Yen, Shuo-Wen Chang, Ying-Hua Chu, and 2 more authors

   In 2024 IEEE 42nd VLSI Test Symposium (VTS), Jan 2024

   Bib

   @inproceedings{10538654,
     author = {Lu, Cheng-Che and Chang, Chi-Chih and Yen, Chia-Heng and Chang, Shuo-Wen and Chu, Ying-Hua and Wu, Kai-Chiang and Chao, Mango Chia-Tso},
     booktitle = {2024 IEEE 42nd VLSI Test Symposium (VTS)},
     title = {Transformer and Its Variants for Identifying Good Dice in Bad Neighborhoods},
     year = {2024},
     volume = {},
     number = {},
     pages = {1-7},
     keywords = {Semiconductor device modeling;Deep learning;Linear regression;Very large scale integration;Multilayer perceptrons;Transformers;Manufacturing},
   }

2023

1. 

   Q-YOLOP: Quantization-Aware You Only Look Once for Panoptic Driving Perception

   Chi-Chih Chang, Wei-Cheng Lin, Pei-Shuo Wang, Sheng-Feng Yu, Yu-Chen Lu, and 2 more authors

   In 2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) , Jul 2023

   Bib PDF

   @inproceedings{10222593,
     author = {Chang, Chi-Chih and Lin, Wei-Cheng and Wang, Pei-Shuo and Yu, Sheng-Feng and Lu, Yu-Chen and Lin, Kuan-Cheng and Wu, Kai-Chiang},
     booktitle = { 2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) },
     title = {{ Q-YOLOP: Quantization-Aware You Only Look Once for Panoptic Driving Perception }},
     year = {2023},
     volume = {},
     issn = {},
     pages = {52-56},
     url = {https://doi.ieeecomputersociety.org/10.1109/ICMEW59549.2023.00015},
     publisher = {IEEE Computer Society},
     address = {Los Alamitos, CA, USA},
     month = jul,
   }