Zhang Zhiyuan
Zhang Zhiyuan
Verified email at - Homepage
Cited by
Cited by
Understanding and Improving Layer Normalization
J Xu, X Sun, Z Zhang, G Zhao, J Lin
Advances in Neural Information Processing Systems, 4381-4391, 2019
Pkuseg: A toolkit for multi-domain chinese word segmentation
R Luo, J Xu, Y Zhang, Z Zhang, X Ren, X Sun
arXiv preprint arXiv:1906.11455, 2019
Raise a child in large language model: Towards effective and generalizable fine-tuning
R Xu, F Luo, Z Zhang, C Tan, B Chang, S Huang, F Huang
arXiv preprint arXiv:2109.05687, 2021
Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models
W Yang, L Li, Z Zhang, X Ren, X Sun, B He
arXiv preprint arXiv:2103.15543, 2021
Rethinking Skip Connection with Layer Normalization
F Liu, X Ren, Z Zhang, X Sun, Y Zou
Proceedings of the 28th International Conference on Computational …, 2020
Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection
G Zhao, J Lin, Z Zhang, X Ren, Q Su, X Sun
arXiv preprint arXiv:1912.11637, 2019
MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
G Zhao, X Sun, J Xu, Z Zhang, L Luo
arXiv preprint arXiv:1911.09483, 2019
Pretrain-KGE: learning knowledge representation from pretrained language models
Z Zhang, X Liu, Y Zhang, Q Su, X Sun, B He
Findings of the Association for Computational Linguistics: EMNLP 2020, 259-266, 2020
Exploring the vulnerability of deep neural networks: A study of parameter corruption
X Sun, Z Zhang, X Ren, R Luo, L Li
Proceedings of the AAAI Conference on Artificial Intelligence 35 (13), 11648 …, 2021
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data
Z Zhang, L Lyu, W Wang, L Sun, X Sun
arXiv preprint arXiv:2109.01300, 2021
Automatic translating between ancient Chinese and contemporary Chinese with limited aligned corpora
Z Zhang, W Li, Q Su
Natural Language Processing and Chinese Computing: 8th CCF International …, 2019
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
Z Zhang, L Lyu, X Ma, C Wang, X Sun
arXiv preprint arXiv:2210.09545, 2022
Memorized sparse backpropagation
Z Zhang, P Yang, X Ren, Q Su, X Sun
Neurocomputing 415, 397-407, 2020
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
S Chen, W Yang, Z Zhang, X Bi, X Sun
arXiv preprint arXiv:2210.07907, 2022
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects
Z Zhang, X Ren, Q Su, X Sun, B He
Proceedings of the 2021 Conference of the North American Chapter of the …, 2021
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation
Z Zhang, Q Su, X Sun
arXiv preprint arXiv:2210.06894, 2022
GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization
Z Zhang, R Luo, Q Su, X Sun
arXiv preprint arXiv:2210.06895, 2022
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
Z Zhang, D Chen, H Zhou, F Meng, J Zhou, X Sun
arXiv preprint arXiv:2305.04547, 2023
Adversarial parameter defense by multi-step risk minimization
Z Zhang, R Luo, X Ren, Q Su, L Li, X Sun
Neural Networks 144, 154-163, 2021
Building an ellipsis-aware chinese dependency treebank for web text
X Ren, X Sun, J Wen, B Wei, W Zhan, Z Zhang
arXiv preprint arXiv:1801.06613, 2018
The system can't perform the operation now. Try again later.
Articles 1–20