2024

1. 

   ICME’24

   The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network

   Zhongzhan Huang, Senwei Liang, Mingfu Liang, Wei He, Haizhao Yang, and Liang Lin

   In IEEE International Conference on Multimedia & Expo (ICME Oral), 2024

   PDF Code

   @inproceedings{huang2022lottery,
     title = {The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network},
     author = {Huang, Zhongzhan and Liang, Senwei and Liang, Mingfu and He, Wei and Yang, Haizhao and Lin, Liang},
     booktitle = {IEEE International Conference on Multimedia & Expo (<strong>ICME</strong> <strong style="color:red;">Oral</strong>)},
     year = {2024},
   }

2. 

   CVPR’24

   Let’s Think Outside the Box: Exploring Leap-of-Thought in LLMs with Creative Humor Generation

   Shanshan Zhong, (co-first) Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, and Pan Zhou

   In The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   PDF Code

   @inproceedings{scale,
     title = {Let’s Think Outside the Box: Exploring Leap-of-Thought in LLMs with Creative Humor Generation},
     author = {Zhong, Shanshan and Huang, (co-first) Zhongzhan and Gao, Shanghua and Wen, Wushao and Lin, Liang and Zitnik, Marinka and Zhou, Pan},
     booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (<strong>CVPR</strong>)},
     year = {2024},
   }

3. 

   WWW’24

   Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima

   Shanshan Zhong, (co-first) Zhongzhan Huang, Daifeng Li, Wushao Wen, Jinghui Qin, and Liang Lin

   In International World Wide Web Conference (WWW), 2024

   PDF Code

   @inproceedings{mg,
     title = {Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima},
     author = {Zhong, Shanshan and Huang, (co-first) Zhongzhan and Li, Daifeng and Wen, Wushao and Qin, Jinghui and Lin, Liang},
     booktitle = {International World Wide Web Conference  (<strong>WWW</strong>)},
     year = {2024}
   }

2023

1. 

   NeurIPS’23

   ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection

   Zhongzhan Huang, Pan Zhou, Shuicheng Yan, and Liang Lin

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

   PDF Code

   @inproceedings{scalf,
     title = {ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection},
     author = {Huang, Zhongzhan and Zhou, Pan and Yan, Shuicheng and Lin, Liang},
     booktitle = {The Conference on Neural Information Processing Systems (<strong>NeurIPS</strong>)},
     year = {2023},
   }

2. 

   Sci. Reports

   On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver

   Zhongzhan Huang, Senwei Liang, Hong Zhang, Haizhao Yang, and Liang Lin

   In Scientific Reports (Sci. Reports), 2023

   arXiv Code

   @inproceedings{huang2022accelerating,
     title = {On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver},
     author = {Huang, Zhongzhan and Liang, Senwei and Zhang, Hong and Yang, Haizhao and Lin, Liang},
     booktitle = {Scientific Reports (<strong>Sci. Reports</strong>)},
     year = {2023}
   }

3. 

   ACM MM’23

   SUR-adapter: Enhancing text-to-image pre-trained diffusion models with large language models

   Shanshan Zhong, (co-first) Zhongzhan Huang, Wushao Wen, Jinghui Qin, and Liang Lin

   In 31th ACM International Conference on Multimedia (ACM MM Oral), 2023

   arXiv Code

   @inproceedings{zhong2023adapter,
     title = {SUR-adapter: Enhancing text-to-image pre-trained diffusion models with large language models},
     author = {Zhong, Shanshan and Huang, (co-first) Zhongzhan and Wen, Wushao and Qin, Jinghui and Lin, Liang},
     booktitle = {31th ACM International Conference on Multimedia (<strong>ACM MM </strong> <strong style="color:red;">Oral</strong>)},
     year = {2023},
     organization = {ACM Press}
   }

4. 

   ICCV’23

   Understanding Self-attention Mechanism via Dynamical System Perspective

   Zhongzhan Huang, Mingfu Liang, Jinghui Qin, Shanshan Zhong, and Liang Lin

   In The IEEE/CVF International Conference on Computer Vision (ICCV), 2023

   arXiv

   @inproceedings{huang2023understanding,
     title = {Understanding Self-attention Mechanism via Dynamical System Perspective},
     author = {Huang, Zhongzhan and Liang, Mingfu and Qin, Jinghui and Zhong, Shanshan and Lin, Liang},
     booktitle = {The IEEE/CVF International Conference on Computer Vision (<strong>ICCV</strong>)},
     year = {2023}
   }

5. 

   Neurocomp.

   ESA: Excitation-Switchable Attention for convolutional neural networks

   Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Zhijing Yang, and Jinghui Qin

   In Neurocomputing (Neurocomp.), 2023

   arXiv Code

   @inproceedings{zhong2023esa,
     title = {ESA: Excitation-Switchable Attention for convolutional neural networks},
     author = {Zhong, Shanshan and Huang, Zhongzhan and Wen, Wushao and Yang, Zhijing and Qin, Jinghui},
     booktitle = {Neurocomputing (<strong>Neurocomp.</strong>)},
     pages = {126706},
     year = {2023},
     publisher = {Elsevier}
   }

6. 

   ICME’23

   LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem

   Shanshan Zhong, Wushao Wen, Jinghui Qin, Qiangpu Chen, and Zhongzhan Huang

   In IEEE International Conference on Multimedia & Expo (ICME Oral), 2023

   arXiv Code

   @inproceedings{zhong2023lsas,
     title = {LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem},
     author = {Zhong, Shanshan and Wen, Wushao and Qin, Jinghui and Chen, Qiangpu and Huang, Zhongzhan},
     booktitle = {IEEE International Conference on Multimedia & Expo (<strong>ICME</strong> <strong style="color:red;">Oral</strong>)},
     year = {2023}
   }

2022

1. 

   EMNLP’22

   CEM: Machine-Human Chatting Handoff via Causal-Enhance Module

   Shanshan Zhong, Jinghui Qin, Zhongzhan Huang, and Daifeng Li

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022

   PDF Code

   @inproceedings{zhong2022cem,
     title = {CEM: Machine-Human Chatting Handoff via Causal-Enhance Module},
     author = {Zhong, Shanshan and Qin, Jinghui and Huang, Zhongzhan and Li, Daifeng},
     booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (<strong>EMNLP</strong>)},
     pages = {3242--3253},
     year = {2022}
   }

2. 

   ICLR’22

   Stiffness-aware neural network for learning Hamiltonian systems

   Senwei Liang, Zhongzhan Huang, and Hong Zhang

   In International Conference on Learning Representations (ICLR), 2022

   PDF Code

   @inproceedings{liang2021stiffness,
     title = {Stiffness-aware neural network for learning Hamiltonian systems},
     author = {Liang, Senwei and Huang, Zhongzhan and Zhang, Hong},
     booktitle = {International Conference on Learning Representations (<strong>ICLR</strong>)},
     year = {2022}
   }

2021

1. 

   NeurIPS’21

   Rethinking the Pruning Criteria for Convolutional Neural Network

   Zhongzhan Huang, Wenqi Shao, Xinjiang Wang, Liang Lin, and Ping Luo

   In The Conference on Neural Information Processing Systems (NeurIPS), 2021

   PDF

   @inproceedings{huang2021convolution,
     title = {Rethinking the Pruning Criteria for Convolutional Neural Network},
     author = {Huang, Zhongzhan and Shao, Wenqi and Wang, Xinjiang and Lin, Liang and Luo, Ping},
     booktitle = {The Conference on Neural Information Processing Systems (<strong>NeurIPS</strong>)},
     year = {2021},
   }

2. 

   ICANN’21

   Blending Pruning Criteria for Convolutional Neural Networks

   Wei He, (co-first) Zhongzhan Huang, Mingfu Liang, Senwei Liang, and Haizhao Yang

   In International Conference on Artificial Neural Networks (ICANN), 2021

   PDF

   @inproceedings{he2021blending,
     title = {Blending Pruning Criteria for Convolutional Neural Networks},
     author = {He, Wei and Huang, (co-first) Zhongzhan and Liang, Mingfu and Liang, Senwei and Yang, Haizhao},
     booktitle = {International Conference on Artificial Neural Networks (<strong>ICANN</strong>)},
     year = {2021},
   }

3. 

   ICRA’21

   Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp

   Junfan Lin, Zhongzhan Huang, Keze Wang, Xiaodan Liang, Weiwei Chen, and Liang Lin

   In IEEE International Conference on Robotics and Automation (ICRA), 2021

   PDF Code

   @inproceedings{lin2020continuous,
     title = {Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp},
     author = {Lin, Junfan and Huang, Zhongzhan and Wang, Keze and Liang, Xiaodan and Chen, Weiwei and Lin, Liang},
     year = {2021},
     booktitle = {IEEE International Conference on Robotics and Automation (<strong>ICRA</strong>)}
   }

2020

1. 

   AAAI’20

   Instance enhancement batch normalization: An adaptive regulator of batch noise

   Senwei Liang, (co-first) Zhongzhan Huang, Mingfu Liang, and Haizhao Yang

   In The AAAI Conference on Artificial Intelligence (AAAI), 2020

   PDF Code

   @inproceedings{liang2020instance,
     title = {Instance enhancement batch normalization: An adaptive regulator of batch noise},
     author = {Liang, Senwei and Huang, (co-first) Zhongzhan and Liang, Mingfu and Yang, Haizhao},
     booktitle = {The AAAI Conference on Artificial Intelligence (<strong>AAAI</strong>)},
     year = {2020}
   }

2. 

   AAAI’20

   DIANet: Dense-and-implicit attention network

   Zhongzhan Huang, Senwei Liang, Mingfu Liang, and Haizhao Yang

   In The AAAI Conference on Artificial Intelligence (AAAI), 2020

   PDF Code

   @inproceedings{huang2020dianet,
     title = {DIANet: Dense-and-implicit attention network},
     author = {Huang, Zhongzhan and Liang, Senwei and Liang, Mingfu and Yang, Haizhao},
     booktitle = {The AAAI Conference on Artificial Intelligence (<strong>AAAI</strong>)},
     year = {2020}
   }

preprint

1. 

   Arxiv

   A Generic Shared Attention Mechanism for Various Backbone Neural Networks

   Zhongzhan Huang, Senwei Liang, Mingfu Liang, and Liang Lin

   In arXiv preprint (in submission), preprint

   PDF Code

   @inproceedings{huang2022layer,
     title = {A Generic Shared Attention Mechanism for Various Backbone Neural Networks},
     author = {Huang, Zhongzhan and Liang, Senwei and Liang, Mingfu and Lin, Liang},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

2. 

   Arxiv

   On Robust Numerical Solver for ODE via Self-Attention Mechanism

   Zhongzhan Huang, Mingfu Liang, and Liang Lin

   In arXiv preprint (in submission), preprint

   PDF Code

   @inproceedings{AttSolver1,
     title = {On Robust Numerical Solver for ODE via Self-Attention Mechanism},
     author = {Huang, Zhongzhan and Liang, Mingfu and Lin, Liang},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

3. 

   Arxiv

   ASR: Attention-alike Structural Re-parameterization

   Shanshan Zhong, (co-first) Zhongzhan Huang, Wushao Wen, Jinghui Qin, and Liang Lin

   In arXiv preprint (in submission), preprint

   PDF

   @inproceedings{asr,
     title = {ASR: Attention-alike Structural Re-parameterization},
     author = {Zhong, Shanshan and Huang, (co-first) Zhongzhan and Wen, Wushao and Qin, Jinghui and Lin, Liang},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

4. 

   Arxiv

   Efficient Attention Network: Accelerate Attention by Searching Where to Plug

   Zhongzhan Huang, Senwei Liang, Mingfu Liang, Wei He, and Haizhao Yang

   In arXiv preprint (in submission), preprint

   PDF Code

   @inproceedings{huang2020efficient,
     title = {Efficient Attention Network: Accelerate Attention by Searching Where to Plug},
     author = {Huang, Zhongzhan and Liang, Senwei and Liang, Mingfu and He, Wei and Yang, Haizhao},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

5. 

   Arxiv

   AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training

   Zhongzhan Huang, Mingfu Liang, Senwei Liang, and Wei He

   In arXiv preprint (in submission), preprint

   PDF

   @inproceedings{huang2021altersgd,
     title = {AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training},
     author = {Huang, Zhongzhan and Liang, Mingfu and Liang, Senwei and He, Wei},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

6. 

   Arxiv

   Continuous Value Assignment: A Doubly Robust Data Augmentation for Off-Policy Learning

   Junfan Lin, Zhongzhan Huang, Keze Wang, Lingbo Liu, and Liang Lin

   In arXiv preprint (in submission), preprint

   PDF Code

   @inproceedings{linContinuousValue,
     title = {Continuous Value Assignment: A Doubly Robust Data Augmentation for Off-Policy Learning},
     author = {Lin, Junfan and Huang, Zhongzhan and Wang, Keze and Liu, Lingbo and Lin, Liang},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

7. 

   Arxiv

   MVT: A Data Augmentation Method for Math Word Problem Solvers

   Jinghui Qin, Zhongzhan Huang, and Liang Lin

   In arXiv preprint (in submission), preprint

   PDF Code

   @inproceedings{mvt,
     title = {MVT: A Data Augmentation Method for Math Word Problem Solvers},
     author = {Qin, Jinghui and Huang, Zhongzhan and Lin, Liang},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }

8. 

   Arxiv

   Deepening Neural Networks Implicitly and Locally via Recurrent Attention Strategy

   Shanshan Zhong, Zhongzhan Huang, Wushao Wen, and Liang Lin

   In arXiv preprint (in submission), preprint

   PDF Code

   @inproceedings{ram,
     title = {Deepening Neural Networks Implicitly and Locally via Recurrent Attention Strategy},
     author = {Zhong, Shanshan and Huang, Zhongzhan and Wen, Wushao and Lin, Liang},
     booktitle = {arXiv preprint (in submission)},
     year = {preprint}
   }