Zhiyuan Zhang

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models pdf

Xuancheng Ren, Xu Sun, Bin He, 2021, NAACL.

Adversarial Parameter Defense by Multi-Step Risk Minimization

Liangyou Li, Xuancheng Ren, Qi Su, 2021, Neural Networks.

Rethinking Skip Connection with Layer Normalization in Transformers and ResNets pdf

Yuexian Zou, Xuancheng Ren, Xu Sun, 2021, ArXiv.

A Representation Separation Perspective to Correspondence-Free Unsupervised 3-D Point Cloud Registration

Dingfu Zhou, Xibin Song, Yuchao Dai, 2022, IEEE Geoscience and Remote Sensing Letters.

Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning pdf

Songfang Huang, Baobao Chang, Chuanqi Tan, 2021, EMNLP.

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data pdf

Xu Sun, Lichao Sun, Lingjuan Lyu, 2021, ArXiv.

ASAT: Adaptively Scaled Adversarial Training in Time Series pdf

Ruihan Bao, Xu Sun, Keiko Harimoto, 2021, ArXiv.

Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects

Xuancheng Ren, Qi Su, Bin He, 2021, NAACL.