Publications

2024

1. AAAI

   Channel Merging: Preserving Specialization for Merged Experts

   Mingyang Zhang ,  Jing Liu ,  Ganggui Ding ,  Xinyi Yu ,  Linlin Ou ,  and  Bohan Zhuang

   In AAAI Conference on Artificial Intelligence (AAAI) , 2024

   arXiv Bib

   @inproceedings{zhang2024channel,
     title = {Channel Merging: Preserving Specialization for Merged Experts},
     author = {Zhang, Mingyang and Liu, Jing and Ding, Ganggui and Yu, Xinyi and Ou, Linlin and Zhuang, Bohan},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2024},
   }

2. AAAI

   Numerical Pruning for Efficient Autoregressive Models

   Xuan Shen ,  Zhao Song ,  Yufa Zhou ,  Bo Chen ,  Jing Liu ,  Ruiyi Zhang ,  Ryan A Rossi ,  Hao Tan ,  Tong Yu ,  Xiang Chen ,  Yufan Zhou ,  Tong Sun ,  Pu Zhao ,  Yanzhi Wang ,  and  Jiuxiang Gu

   In AAAI Conference on Artificial Intelligence (AAAI) , 2024

   arXiv Bib

   @inproceedings{shen2024numerical,
     title = {Numerical Pruning for Efficient Autoregressive Models},
     author = {Shen, Xuan and Song, Zhao and Zhou, Yufa and Chen, Bo and Liu, Jing and Zhang, Ruiyi and Rossi, Ryan A and Tan, Hao and Yu, Tong and Chen, Xiang and Zhou, Yufan and Sun, Tong and Zhao, Pu and Wang, Yanzhi and Gu, Jiuxiang},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2024},
   }

3. NeurIPS

   MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

   Akide Liu ,  Jing Liu ,  Zizheng Pan ,  Yefei He ,  Gholamreza Haffari ,  and  Bohan Zhuang

   In Conference on Neural Information Processing Systems (NeurIPS) , 2024

   arXiv Bib

   @inproceedings{liu2024minicache,
     title = {MiniCache: KV Cache Compression in Depth Dimension for Large Language Models},
     author = {Liu, Akide and Liu, Jing and Pan, Zizheng and He, Yefei and Haffari, Gholamreza and Zhuang, Bohan},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     year = {2024},
   }

4. NeurIPS

   ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

   Yefei He ,  Luoming Zhang ,  Weijia Wu ,  Jing Liu ,  Hong Zhou ,  and  Bohan Zhuang

   In Conference on Neural Information Processing Systems (NeurIPS) , 2024

   arXiv Bib Code

   @inproceedings{he2024zipcache,
     title = {ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification},
     author = {He, Yefei and Zhang, Luoming and Wu, Weijia and Liu, Jing and Zhou, Hong and Zhuang, Bohan},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     year = {2024},
   }

5. ECCV

   Stitched ViTs are Flexible Vision Backbones

   Zizheng Pan ,  Jing Liu ,  Haoyu He ,  Jianfei Cai ,  and  Bohan Zhuang

   In European Conference on Computer Vision (ECCV) , 2024

   arXiv Bib Code

   @inproceedings{pan2023snnetv2,
     title = {Stitched ViTs are Flexible Vision Backbones},
     author = {Pan, Zizheng and Liu, Jing and He, Haoyu and Cai, Jianfei and Zhuang, Bohan},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2024},
   }

6. CVPR

   Efficient Stitchable Task Adaptation

   Haoyu He ,  Zizheng Pan ,  Jing Liu ,  Jianfei Cai ,  and  Bohan Zhuang

   In Conference on Computer Vision and Pattern Recognition (CVPR) , 2024

   arXiv Bib Code

   @inproceedings{he2023efficient,
     title = {Efficient Stitchable Task Adaptation},
     author = {He, Haoyu and Pan, Zizheng and Liu, Jing and Cai, Jianfei and Zhuang, Bohan},
     booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2024},
   }

7. CVPR Highlight

   Tfmq-dm: Temporal feature maintenance quantization for diffusion models

   Yushi Huang* ,  Ruihao Gong* ,  Jing Liu ,  Tianlong Chen ,  and  Xianglong Liu

   In Conference on Computer Vision and Pattern Recognition (CVPR) , 2024

   Spotlight (top 11% of the accepted papers)

   arXiv Bib Code

   @inproceedings{huang2023tfmq,
     title = {Tfmq-dm: Temporal feature maintenance quantization for diffusion models},
     author = {Huang*, Yushi and Gong*, Ruihao and Liu, Jing and Chen, Tianlong and Liu, Xianglong},
     booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2024},
     price = {Highlight},
     long_price = {Spotlight (top 11% of the accepted papers)},
   }

8. ICLR

   QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models

   Jing Liu ,  Ruihao Gong ,  Xiuying Wei ,  Zhiwei Dong ,  Jianfei Cai ,  and  Bohan Zhuang

   In International Conference on Learning Representations (ICLR) , 2024

   arXiv Bib Code

   @inproceedings{liu2024qllm,
     title = {{QLLM}: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models},
     author = {Liu, Jing and Gong, Ruihao and Wei, Xiuying and Dong, Zhiwei and Cai, Jianfei and Zhuang, Bohan},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2024},
   }

9. ICLR Spotlight

   EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

   Yefei He ,  Jing Liu ,  Weijia Wu ,  Hong Zhou ,  and  Bohan Zhuang

   In International Conference on Learning Representations (ICLR) , 2024

   Spotlight (top 5% of the accepted papers)

   arXiv Bib

   @inproceedings{he2024efficientdm,
     title = {Efficient{DM}: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models},
     author = {He, Yefei and Liu, Jing and Wu, Weijia and Zhou, Hong and Zhuang, Bohan},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2024},
     price = {Spotlight},
     long_price = {Spotlight (top 5% of the accepted papers)}
   }

2023

1. TPAMI

   Pruning self-attentions into convolutional layers in single path

   Haoyu He ,  Jing Liu ,  Zizheng Pan ,  Jianfei Cai ,  Jing Zhang ,  Dacheng Tao ,  and  Bohan Zhuang

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023

   arXiv Bib

   @article{he2021pruning,
     title = {Pruning self-attentions into convolutional layers in single path},
     author = {He, Haoyu and Liu, Jing and Pan, Zizheng and Cai, Jianfei and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
     year = {2023},
   }

2. NeurIPS

   PTQD: Accurate Post-Training Quantization for Diffusion Models

   Yefei He ,  Luping Liu ,  Jing Liu ,  Weijia Wu ,  Hong Zhou ,  and  Bohan Zhuang

   In Conference on Neural Information Processing Systems (NeurIPS) , 2023

   arXiv Bib Code

   @inproceedings{he2023ptqd,
     title = {{PTQD}: Accurate Post-Training Quantization for Diffusion Models},
     author = {He, Yefei and Liu, Luping and Liu, Jing and Wu, Weijia and Zhou, Hong and Zhuang, Bohan},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     year = {2023},
     url = {https://openreview.net/forum?id=Y3g1PV5R9l},
   }

3. ICCV

   BiViT: Extremely Compressed Binary Vision Transformers

   Yefei He ,  Zhenyu Lou ,  Luoming Zhang ,  Jing Liu ,  Weijia Wu ,  Hong Zhou ,  and  Bohan Zhuang

   In International Conference on Computer Vision (ICCV) , 2023

   arXiv Bib Code

   @inproceedings{he2023bivit,
     title = {BiViT: Extremely Compressed Binary Vision Transformers},
     author = {He, Yefei and Lou, Zhenyu and Zhang, Luoming and Liu, Jing and Wu, Weijia and Zhou, Hong and Zhuang, Bohan},
     booktitle = {International Conference on Computer Vision (ICCV)},
     pages = {5651--5663},
     year = {2023},
   }

4. TPAMI

   Single-path bit sharing for automatic loss-aware model compression

   Jing Liu ,  Bohan Zhuang ,  Peng Chen ,  Chunhua Shen ,  Jianfei Cai ,  and  Mingkui Tan

   IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

   arXiv Bib

   @article{liu2023single,
     title = {Single-path bit sharing for automatic loss-aware model compression},
     author = {Liu, Jing and Zhuang, Bohan and Chen, Peng and Shen, Chunhua and Cai, Jianfei and Tan, Mingkui},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
     year = {2023},
     doi = {10.1109/TPAMI.2023.3275159}
   }

5. IJCAI

   A Survey on Efficient Training of Transformers

   Bohan Zhuang ,  Jing Liu ,  Zizheng Pan ,  Haoyu He ,  Yuetian Weng ,  and  Chunhua Shen

   In International Joint Conference on Artificial Intelligence (IJCAI) , 2023

   Survey Track

   arXiv Bib

   @inproceedings{ijcai2023p764,
     title = {A Survey on Efficient Training of Transformers},
     author = {Zhuang, Bohan and Liu, Jing and Pan, Zizheng and He, Haoyu and Weng, Yuetian and Shen, Chunhua},
     booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
     pages = {6823--6831},
     year = {2023},
     note = {Survey Track},
     doi = {10.24963/ijcai.2023/764},
   }

6. CVPR

   Dynamic Focus-Aware Positional Queries for Semantic Segmentation

   Haoyu He ,  Jianfei Cai ,  Zizheng Pan ,  Jing Liu ,  Jing Zhang ,  Dacheng Tao ,  and  Bohan Zhuang

   In Conference on Computer Vision and Pattern Recognition (CVPR) , 2023

   arXiv Bib

   @inproceedings{He_2023_CVPR,
     author = {He, Haoyu and Cai, Jianfei and Pan, Zizheng and Liu, Jing and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan},
     title = {Dynamic Focus-Aware Positional Queries for Semantic Segmentation},
     booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2023},
     pages = {11299-11308},
   }

2022

1. NeurIPS Spotlight

   EcoFormer: Energy-Saving Attention with Linear Complexity

   Jing Liu* ,  Zizheng Pan* ,  Haoyu He ,  Jianfei Cai ,  and  Bohan Zhuang

   In Conference on Neural Information Processing Systems (NeurIPS) , 2022

   Spotlight (top 5% of the accepted papers)

   arXiv Bib Code

   @inproceedings{liu2022ecoformer,
     author = {Liu*, Jing and Pan*, Zizheng and He, Haoyu and Cai, Jianfei and Zhuang, Bohan},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     pages = {10295--10308},
     title = {EcoFormer: Energy-Saving Attention with Linear Complexity},
     volume = {35},
     year = {2022},
     price = {Spotlight},
     long_price = {Spotlight (top 5% of the accepted papers)},
   }

2. AAAI

   Less is more: Pay less attention in vision transformers

   Zizheng Pan ,  Bohan Zhuang ,  Haoyu He ,  Jing Liu ,  and  Jianfei Cai

   In AAAI Conference on Artificial Intelligence (AAAI) , 2022

   arXiv Bib Code

   @inproceedings{pan2022less,
     title = {Less is more: Pay less attention in vision transformers},
     author = {Pan, Zizheng and Zhuang, Bohan and He, Haoyu and Liu, Jing and Cai, Jianfei},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     volume = {36},
     number = {2},
     pages = {2035--2043},
     year = {2022},
   }

2021

1. ICCV

   Scalable Vision Transformers With Hierarchical Pooling

   Zizheng Pan ,  Bohan Zhuang ,  Jing Liu ,  Haoyu He ,  and  Jianfei Cai

   In International Conference on Computer Vision (ICCV) , 2021

   arXiv Bib Code

   @inproceedings{Pan_2021_ICCV,
     author = {Pan, Zizheng and Zhuang, Bohan and Liu, Jing and He, Haoyu and Cai, Jianfei},
     title = {Scalable Vision Transformers With Hierarchical Pooling},
     booktitle = {International Conference on Computer Vision (ICCV)},
     year = {2021},
     pages = {377-386},
   }

2. arXiv

   Sharpness-aware quantization for deep neural networks

   Jing Liu ,  Jianfei Cai ,  and  Bohan Zhuang

   arXiv preprint arXiv:2111.12273, 2021

   arXiv Bib Code

   @article{liu2021sharpness,
     title = {Sharpness-aware quantization for deep neural networks},
     author = {Liu, Jing and Cai, Jianfei and Zhuang, Bohan},
     booktitle = {arXiv},
     journal = {arXiv preprint arXiv:2111.12273},
     year = {2021},
   }

3. arXiv

   Mesa: A memory-saving training framework for transformers

   Zizheng Pan ,  Peng Chen ,  Haoyu He ,  Jing Liu ,  Jianfei Cai ,  and  Bohan Zhuang

   arXiv preprint arXiv:2111.11124, 2021

   arXiv Bib Code

   @article{pan2021mesa,
     title = {Mesa: A memory-saving training framework for transformers},
     author = {Pan, Zizheng and Chen, Peng and He, Haoyu and Liu, Jing and Cai, Jianfei and Zhuang, Bohan},
     journal = {arXiv preprint arXiv:2111.11124},
     year = {2021},
   }

4. TPAMI

   Discrimination-aware network pruning for deep model compression

   Jing Liu* ,  Bohan Zhuang* ,  Zhuangwei Zhuang* ,  Yong Guo ,  Junzhou Huang ,  Jinhui Zhu ,  and  Mingkui Tan*

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

   arXiv Bib Code

   @article{liu2021discrimination,
     title = {Discrimination-aware network pruning for deep model compression},
     author = {Liu*, Jing and Zhuang*, Bohan and Zhuang*, Zhuangwei and Guo, Yong and Huang, Junzhou and Zhu, Jinhui and Tan*, Mingkui},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
     volume = {44},
     number = {8},
     pages = {4035--4051},
     year = {2021},
   }

5. TPAMI

   Effective training of convolutional neural networks with low-bitwidth weights and activations

   Bohan Zhuang* ,  Mingkui Tan* ,  Jing Liu* ,  Lingqiao Liu ,  Ian Reid ,  and  Chunhua Shen

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

   arXiv Bib Code

   @article{zhuang2021effective,
     title = {Effective training of convolutional neural networks with low-bitwidth weights and activations},
     author = {Zhuang*, Bohan and Tan*, Mingkui and Liu*, Jing and Liu, Lingqiao and Reid, Ian and Shen, Chunhua},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
     volume = {44},
     number = {10},
     pages = {6140--6152},
     year = {2021},
   }

6. CVPR Oral

   AQD: Towards Accurate Quantized Object Detection

   Peng Chen* ,  Jing Liu* ,  Bohan Zhuang ,  Mingkui Tan ,  and  Chunhua Shen

   In Conference on Computer Vision and Pattern Recognition (CVPR) , 2021

   Oral Presentation (top 4% of the accepted papers)

   arXiv Bib Code

   @inproceedings{Chen_2021_CVPR,
     author = {Chen*, Peng and Liu*, Jing and Zhuang, Bohan and Tan, Mingkui and Shen, Chunhua},
     title = {AQD: Towards Accurate Quantized Object Detection},
     booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2021},
     pages = {104-113},
     price = {Oral},
     long_price = {Oral Presentation (top 4% of the accepted papers)},
   }

2020

1. ECCV

   Deep transferring quantization

   Zheng Xie* ,  Zhiquan Wen* ,  Jing Liu* ,  Zhiqiang Liu ,  Xixian Wu ,  and  Mingkui Tan

   In European Conference on Computer Vision (ECCV) , 2020

   Bib PDF Code

   @inproceedings{xie2020deep,
     title = {Deep transferring quantization},
     author = {Xie*, Zheng and Wen*, Zhiquan and Liu*, Jing and Liu, Zhiqiang and Wu, Xixian and Tan, Mingkui},
     booktitle = {European Conference on Computer Vision (ECCV)},
     pages = {625--642},
     year = {2020},
   }

2. ECCV

   Generative low-bitwidth data free quantization

   Shoukai Xu* ,  Haokun Li* ,  Bohan Zhuang* ,  Jing Liu ,  Jiezhang Cao ,  Chuangrun Liang ,  and  Mingkui Tan

   In European Conference on Computer Vision (ECCV) , 2020

   arXiv Bib Code

   @inproceedings{xu2020generative,
     title = {Generative low-bitwidth data free quantization},
     author = {Xu*, Shoukai and Li*, Haokun and Zhuang*, Bohan and Liu, Jing and Cao, Jiezhang and Liang, Chuangrun and Tan, Mingkui},
     booktitle = {European Conference on Computer Vision (ECCV)},
     pages = {1--17},
     year = {2020},
   }

2018

1. NeurIPS

   Discrimination-aware Channel Pruning for Deep Neural Networks

   Zhuangwei Zhuang* ,  Mingkui Tan* ,  Bohan Zhuang* ,  Jing Liu* ,  Yong Guo ,  Qingyao Wu ,  Junzhou Huang ,  and  Jinhui Zhu

   In Conference on Neural Information Processing Systems (NeurIPS) , 2018

   arXiv Bib Code

   @incollection{zhuang2018discrimination,
     title = {Discrimination-aware Channel Pruning for Deep Neural Networks},
     author = {Zhuang*, Zhuangwei and Tan*, Mingkui and Zhuang*, Bohan and Liu*, Jing and Guo, Yong and Wu, Qingyao and Huang, Junzhou and Zhu, Jinhui},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     pages = {881--892},
     year = {2018},
   }