Selected publications

Full list can be found here

• Get More at Once: Alternating Sparse Training with Gradient Correction [PDF][Code]
  Li Yang, Jian Meng, Jae-sun Seo, and Deliang Fan
  Thirty-sixth Conference on Neural Information Processing Systems, New Orleans, LA, Nov.29 – Dec.1, 2022 ( The first two authors contribute equally) [NeurIPS’22]

• Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer [PDF]
  Sen Lin, Li Yang, Deliang Fan, and Junshan Zhang
  *Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, Nov.29 – Dec.1, 2022 [NeurIPS’22]

• XMA: a crossbar-aware multi-task adaption framework via shift-based mask learning method [PDF]
  Zhang, Fan, Li Yang, Jian Meng, Jae-sun Seo, Yu Cao, and Deliang Fan
  In Proceedings of the 59th ACM/IEEE Design Automation Conference, pp. 271-276. 2022 [DAC’22]

• Rep-Net: Efficient On-Device Learning via Feature Reprogramming [PDF]
  Li Yang, Adnan Siraj Rakin, and Deliang Fan
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, Louisiana, June 19-24, 2022 [CVPR’22]

• Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning [PDF]
  Meng, Jian, Li Yang, Jinwoo Shin, Deliang Fan, and Jae-sun Seo
  In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12257-12265. 2022 [CVPR’22]

• TRGP: Trust Region Gradient Projection for Continual Learning [PDF]
  Sen Li, Li Yang, Deliang Fan, and Junshan Zhang
  The Tenth International Conference on Learning Representations, (ICLR), Apr. 25- 29th, 2022 [ICLR’22](-spotlight-)

• Gradient-based Novelty Detection Boosted by Self-supervised Binary Classification [PDF]
  Jingbo Sun, Li Yang, Jiaxin Zhang, Frank Liu, Mahantesh Halappanavar, Deliang Fan, and Yu Cao
  Thirty-Six AAAI Conference on Artificial Intelligence (AAAI), Feb. 22-March 1, 2022, Vancouver, BC, Canada [AAAI’22]

• KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning [PDF]
  Li Yang, Zhezhi He, Junshan Zhang and Deliang Fan
  IEEE/CVF Computer Vision and Pattern Recognition (CVPR), June 19-25, 2021 [CVPR’21]

• Non-uniform DNN Structured Subnets Sampling for Dynamic Inference [PDF]
  Li Yang, Zhezhi He, Yu Cao and Deliang Fan
  In: 57th Design Automation Conference (DAC), San Francisco, CA, July 19-23, 2020 [DAC’20]

• Harmonious Coexistence of Structured Weight Pruning and Ternarization for Deep Neural Networks [PDF]
  Li Yang, Zhezhi He and Deliang Fan
  Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), Feb. 7-12 2020, New York, USA [AAAI’20(-spotlight-)]

• A Fully Onchip Binarized Convolutional Neural Network FPGA Implementation with Accurate Inference [PDF]
  Li Yang, Zhezhi He and Deliang Fan
  ACM/IEEE International Symposium on Low Power Electronics and Design, July 23-25, 2018, Bellevue, Washington, USA [ISLPED’18]