Hengzhi Pei

26 papers A* 7C 1Journal 13Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Connecting the Impact of Silent Data Corruption With Different Training Characteristics: An Empirical Study.
IEEE Micro
Hengzhi Pei, Leonard Lausen, George Karypis
2025 — conf
Understanding Silent Data Corruption in LLM Training.
ACL (1)
Jeffrey Jian Ma, Hengzhi Pei, Leonard Lausen, George Karypis
2025 J jnl
Understanding Silent Data Corruption in LLM Training.
CoRR
Jeffrey Jian Ma, Hengzhi Pei, Leonard Lausen, George Karypis
2025 C conf
When Silicon Fails Silently: Characterizing Hardware-Induced Corruption in LLM Training.
IOLTS
Jeffrey Jian Ma, Hengzhi Pei, Leonard Lausen, George Karypis
2024 — conf
Fine-tuning Language Models for Joint Rewriting and Completion of Code with Potential Bugs.
ACL (Findings)
Dingmin Wang, Jinman Zhao, Hengzhi Pei, Samson Tan, Sheng Zha
2024 A* conf
TextGuard: Provable Defense against Backdoor Attacks on Text Classification.
NDSS
Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song
2023 A* conf
Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion.
AAAI
Hengzhi Pei, Jinman Zhao, Leonard Lausen, Sheng Zha, George Karypis
2023 J jnl
Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion.
CoRR
Hengzhi Pei, Jinman Zhao, Leonard Lausen, Sheng Zha, George Karypis
2023 A* conf
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models.
NeurIPS
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
2023 J jnl
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models.
CoRR
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li
2023 J jnl
TextGuard: Provable Defense against Backdoor Attacks on Text Classification.
CoRR
Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song
2023 — conf
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations.
ACL (Findings)
Chi Han, Hengzhi Pei, Xinya Du, Heng Ji
2022 A* conf
Improving Certified Robustness via Statistical Learning with Logical Reasoning.
NeurIPS
Zhuolin Yang, Zhikuan Zhao, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlas, Ji Liu, Heng Guo, Ce Zhang, Bo Li
2022 J jnl
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One.
CoRR
Yezhen Wang, Tong Che, Bo Li, Kaitao Song, Hengzhi Pei, Yoshua Bengio, Dongsheng Li
2022 J jnl
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations.
CoRR
Chi Han, Hengzhi Pei, Xinya Du, Heng Ji
2021 A* conf
Towards Generating Real-World Time Series Data.
ICDM
Hengzhi Pei, Kan Ren, Yuqing Yang, Chang Liu, Tao Qin, Dongsheng Li
2021 J jnl
Towards Generating Real-World Time Series Data.
CoRR
Hengzhi Pei, Kan Ren, Yuqing Yang, Chang Liu, Tao Qin, Dongsheng Li
2020 — conf
A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder.
EMNLP (Findings)
Xipeng Qiu, Hengzhi Pei, Hang Yan, Xuanjing Huang
2020 J jnl
End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines.
CoRR
Zhuolin Yang, Zhikuan Zhao, Hengzhi Pei, Boxin Wang, Bojan Karlas, Ji Liu, Heng Guo, Bo Li, Ce Zhang
2020 A* conf
Reinforcement-Learning Based Portfolio Management with Augmented Asset Movement Prediction States.
AAAI
Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Ju Xiao, Bo Li
2020 J jnl
Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States.
CoRR
Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Jun Xiao, Bo Li
2020 — conf
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack.
EMNLP (1)
Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li
2020 A* conf
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks.
CVPR
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song
2019 J jnl
AdvCodec: Towards A Unified Framework for Adversarial Text Generation.
CoRR
Boxin Wang, Hengzhi Pei, Han Liu, Bo Li
2019 J jnl
Multi-Criteria Chinese Word Segmentation with Transformer.
CoRR
Xipeng Qiu, Hengzhi Pei, Hang Yan, Xuanjing Huang
2019 J jnl
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks.
CoRR
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song