Publications

2025

1. 

   xKV: Cross-Layer SVD for KV-Cache Compression

   Chi-Chih Chang, Chien-Yu Lin, Yash Akhauri, and 4 more authors

   2025

   Bib PDF Code

   @misc{chang2025xkv,
     title = {xKV: Cross-Layer SVD for KV-Cache Compression },
     author = {Chang, Chi-Chih and Lin, Chien-Yu and Akhauri, Yash and Lin, Wei-Cheng and Wu, Kai-Chiang and Ceze, Luis and Abdelfattah, Mohamed S.},
     journal = {ArXiv},
     year = {2025},
     eprint = {2503.18893},
   }

2. xKV: Cross-Layer SVD for KV-Cache Compression

   2025

3. 

   TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval

   Chien-Yu Lin^*, Keisuke Kamahori^*, Yiyu Liu, and 11 more authors

   2025

   Bib PDF

   @article{lin2025telerag,
     title = {TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval},
     author = {Lin, Chien-Yu and Kamahori, Keisuke and Liu, Yiyu and Shi, Xiaoxiang and Kashyap, Madhav and Gu, Yile and Shao, Rulin and Ye, Zihao and Zhu, Kan and Wang, Stephanie and Krishnamurthy, Arvind and Kadekodi, Rohan and Ceze, Luis and Kasikci, Baris},
     venue_url = {https://arxiv.org/abs/2502.20969},
     year = {2025},
   }

4. 

   Palu: Compressing KV-Cache with Low-Rank Projection

   Chi-Chih Chang^*, Wei-Cheng Lin^*, Chien-Yu Lin^*, and 7 more authors

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

   Bib PDF

   @inproceedings{chang2024palu,
     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 Abdelfattah, Mohamed S. and Wu, Kai-Chiang},
     booktitle = {Proceedings of International Conference on Learning Representations (ICLR)},
     title = {Palu: Compressing KV-Cache with Low-Rank Projection},
     year = {2025},
     venue_url = {https://arxiv.org/abs/2407.21118},
   }

5. 

   NanoFlow: Towards Optimal Large Language Model Serving Throughput

   Kan Zhu, Yilong Zhao, Liangyu Zhao, and 12 more authors

   In 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2025, 2025

   Bib PDF Code

   @inproceedings{zhu2024nanoflow,
     title = {NanoFlow: Towards Optimal Large Language Model Serving Throughput},
     author = {Zhu, Kan and Zhao, Yilong and Zhao, Liangyu and Zuo, Gefei and Gu, Yile and Xie, Dedong and Gao, Yufei and Xu, Qinyu and Tang, Tian and Ye, Zihao and Kamahori, Keisuke and Lin, Chien-Yu and Wang, Stephanie and Krishnamurthy, Arvind and Kasikci, Baris},
     booktitle = {19th USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2025},
     year = {2025},
     eprint = {2408.12757},
   }

2024

1. 

   Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks

   Bo-Ru Lu, Nikita Haduong, Chien-Yu Lin, and 3 more authors

   arXiv preprint arXiv:2403.13112, 2024

   Bib PDF

   @article{lu2024efficient,
     title = {Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks},
     author = {Lu, Bo-Ru and Haduong, Nikita and Lin, Chien-Yu and Cheng, Hao and Smith, Noah A. and Ostendorf, Mari},
     journal = {arXiv preprint arXiv:2403.13112},
     year = {2024},
   }

2. 

   Atom: Low-Bit Quantization for Efficient and Accurate LLM Serving

   Yilong Zhao, Chien-Yu Lin, Kan Zhu, and 7 more authors

   In Proceedings of Machine Learning and Systems (MLSys), 2024

   Bib PDF Code

   @inproceedings{zhao2024atom,
     author = {Zhao, Yilong and Lin, Chien-Yu and Zhu, Kan and Ye, Zihao and Chen, Lequn and Zheng, Size and Ceze, Luis and Krishnamurthy, Arvind and Chen, Tianqi and Kasikci, Baris},
     booktitle = {Proceedings of Machine Learning and Systems (MLSys)},
     pages = {196--209},
     title = {Atom: Low-Bit Quantization for Efficient and Accurate LLM Serving},
     url = {https://proceedings.mlsys.org/paper_files/paper/2024/file/5edb57c05c81d04beb716ef1d542fe9e-Paper-Conference.pdf},
     volume = {6},
     year = {2024},
   }

3. 

   FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline

   Chien-Yu Lin, Qichen Fu, Thomas Merth, and 2 more authors

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

   Oral (Top 2.6%)

   Bib PDF

   @inproceedings{lin2024fastsrnerf,
     author = {Lin, Chien-Yu and Fu, Qichen and Merth, Thomas and Yang, Karren and Ranjan, Anurag},
     title = {FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline},
     booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
     month = jan,
     year = {2024},
     pages = {2482-2491},
     venue_type = {Conference},
   }

2022

1. 

   SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks

   Chien-Yu Lin^*, Anish Prabhu^*, Thomas Merth, and 4 more authors

   In Proceedings the 17th European Conference on Computer Vision (ECCV), Jan 2022

   Bib PDF Video Code

   @inproceedings{lin2022spin,
     author = {Lin, Chien-Yu and Prabhu, Anish and Merth, Thomas and Mehta, Sachin and Ranjan, Anurag and Horton, Maxwell and Rastegari, Mohammad},
     title = {SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks},
     booktitle = {Proceedings the 17th European Conference on Computer Vision (ECCV)},
     year = {2022},
     venue_type = {Conference},
   }

2021

1. 

   Accelerating Spmm Kernel with Cache-First Edge Sampling for Graph Neural Networks

   Chien-Yu Lin, Liang Luo, and Luis Ceze

   arXiv preprint arXiv:2104.10716, Jan 2021

   Bib PDF

   @article{lin2021esspmm,
     title = {Accelerating Spmm Kernel with Cache-First Edge Sampling for Graph Neural Networks},
     author = {Lin, Chien-Yu and Luo, Liang and Ceze, Luis},
     journal = {arXiv preprint arXiv:2104.10716},
     year = {2021},
     venue_type = {ArXiv},
   }

2019

1. 

   Enhancing Utilization of SIMD-Like Accelerator for Sparse Convolutional Neural Networks

   Bo-Cheng Lai, Jyun-Wei Pan, and Chien-Yu Lin

   IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Jan 2019

   Bib PDF

   @article{lai2019enhancing,
     title = {Enhancing Utilization of SIMD-Like Accelerator for Sparse Convolutional Neural Networks},
     author = {Lai, Bo-Cheng and Pan, Jyun-Wei and Lin, Chien-Yu},
     journal = {IEEE Transactions on Very Large Scale Integration (VLSI) Systems},
     year = {2019},
   }

2018

1. 

   Supporting compressed-sparse activations and weights on SIMD-like accelerator for sparse convolutional neural networks

   Chien-Yu Lin, and Bo-Cheng Lai

   In Proceedings of the 23rd Asia and South Pacific Design Automation Conference (ASP-DAC), Jan 2018

   Bib PDF Slides

   @inproceedings{lin2018supporting,
     author = {Lin, Chien-Yu and Lai, Bo-Cheng},
     title = {Supporting compressed-sparse activations and weights on SIMD-like accelerator for sparse convolutional neural networks},
     booktitle = {Proceedings of the 23rd Asia and South Pacific Design Automation Conference (ASP-DAC)},
     year = {2018},
   }