Yao Qiang

发表

Adversarially robust and explainable model compression with on-device personalization for NLP applications

Supriya Tumkur Suresh Kumar, D. Zhu, Marco Brocanelli, 2021 .

Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN

D. Zhu, Marco Brocanelli, Yao Qiang, 2022, IJCAI.

AttCAT: Explaining Transformers via Attentive Class Activation Tokens

D. Zhu, X. Li, Rhongho Jang, 2022, NeurIPS.

Negative Flux Aggregation to Estimate Feature Attributions

D. Zhu, X. Li, Yao Qiang, 2023, ArXiv.

Negative Flux Aggregation to Estimate Feature Attributions

D. Zhu, X. Li, Yao Qiang, 2023, ArXiv.

Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification pdf

Dongxiao Zhu, Yao Qiang, Marco Brocanelli, 2021, ArXiv.

Fairness-aware Vision Transformer via Debiased Self-Attention

D. Zhu, Yao Qiang, Chengyin Li, 2023, ArXiv.

Fairness-aware Vision Transformer via Debiased Self-Attention

D. Zhu, Yao Qiang, Chengyin Li, 2023, ArXiv.

Hijacking Large Language Models via Adversarial In-Context Learning

Yao Qiang, Xiangyu Zhou, Dongxiao Zhu, 2023, ArXiv.

Learning Compact Features via In-Training Representation Alignment

D. Zhu, X. Li, Xiangrui Li, 2022, AAAI.

Tiny RNN Model with Certified Robustness for Text Classification

Supriya Tumkur Suresh Kumar, D. Zhu, Marco Brocanelli, 2022, 2022 International Joint Conference on Neural Networks (IJCNN).

Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Dongxiao Zhu, Xin Li, Yao Qiang, 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

FedDRO: Federated Compositional Optimization for Distributionally Robust Learning

Rafi Ibn Sultan, Yao Qiang, Chengyin Li, 2023, arXiv.org.

Adversarially robust and explainable model compression with on-device personalization for NLP applications

Supriya Tumkur Suresh Kumar, D. Zhu, Marco Brocanelli, 2021 .