HP
Hengzhi Pei
cs.LGcs.AIcs.CLcs.CRstat.MLcs.ARcs.CYcs.DCcs.PFcs.SE
On Valency
published · living versionsW_auaupkkt·v1 · currentpublished
-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation
with Bowen Fang, Dingmin Wang
1 version
Preprints & journals
14 papers in the corpus · 2019–2026KernelSight-LM: A Kernel-Level LLM Inference Simulator2606.28565v2 · Xiteng Yao, Taeho Kim, Hengzhi Pei et al.2026 · 0 citationsarXiv
The Amazon Nova Family of Models: Technical Report and Model Card2506.12103v1 · Amazon AGI, Aaron Langford, Aayush Shah et al.2025 · 2 citationsarXiv
Understanding Silent Data Corruption in LLM Training2502.12340v1 · Jeffrey Ma, Hengzhi Pei, Leonard Lausen et al.2025 · 12 citationsarXiv
TextGuard: Provable Defense against Backdoor Attacks on Text Classification2311.11225v2 · Hengzhi Pei, Jinyuan Jia, Wenbo Guo et al.2023 · 15 citationsarXiv
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models2306.11698v5 · Boxin Wang, Weixin Chen, Hengzhi Pei et al.2023 · 105 citationsarXiv
Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion2306.00381v1 · Hengzhi Pei, Jinman Zhao, Leonard Lausen et al.2023 · 10 citationsarXiv
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations2211.03252v2 · Chi Han, Hengzhi Pei, Xinya Du et al.2022 · 2 citationsarXiv
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One2206.12840v1 · Yezhen Wang, Tong Che, Bo Li et al.2022 · 0 citationsarXiv
Towards Generating Real-World Time Series Data2111.08386v1 · Hengzhi Pei, Kan Ren, Yuqing Yang et al.2021 · 54 citationsarXiv
Improving Certified Robustness via Statistical Learning with Logical Reasoning2003.00120v9 · Zhuolin Yang, Zhikuan Zhao, Boxin Wang et al.2020 · 6 citationsarXiv
Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States2002.05780v1 · Yunan Ye, Hengzhi Pei, Boxin Wang et al.2020 · 176 citationsarXiv
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack1912.10375v2 · Boxin Wang, Hengzhi Pei, Boyuan Pan et al.2019 · 56 citationsarXiv
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks1911.07135v2 · Yuheng Zhang, Ruoxi Jia, Hengzhi Pei et al.2019 · 465 citationsarXiv
A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder1906.12035v2 · Xipeng Qiu, Hengzhi Pei, Hang Yan et al.2019 · 32 citationsarXiv
Career total: 20 works. 14 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.