Pengyu Cheng

Pengyu Cheng

Duke University

H-index: 10

North America-United States

About Pengyu Cheng

Pengyu Cheng, With an exceptional h-index of 10 and a recent h-index of 10 (since 2020), a distinguished researcher at Duke University, specializes in the field of machine learning, natural language processing.

His recent articles reflect a diverse array of research interests and contributions to the field:

Self-playing Adversarial Language Game Enhances LLM Reasoning

On Diversified Preferences of Large Language Model Alignment

Adversarial preference optimization

Everyone Deserves A Reward: Learning Customized Human Preferences

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers

Toward fairness in text generation via mutual information minimization based on importance sampling

Replacing language model for style transfer

Waffle: Weight anonymized factorization for federated learning

Pengyu Cheng Information

University

Position

Ph.D. student

Citations(all)

665

Citations(since 2020)

663

Cited By

82

hIndex(all)

10

hIndex(since 2020)

10

i10Index(all)

11

i10Index(since 2020)

11

Email

University Profile Page

Google Scholar

Pengyu Cheng Skills & Research Interests

machine learning

natural language processing

Top articles of Pengyu Cheng

Self-playing Adversarial Language Game Enhances LLM Reasoning

arXiv preprint arXiv:2404.10642

2024/4/16

On Diversified Preferences of Large Language Model Alignment

arXiv preprint arXiv:2312.07401

2023/12/12

Adversarial preference optimization

arXiv preprint arXiv:2311.08045

2023/11/14

Everyone Deserves A Reward: Learning Customized Human Preferences

arXiv preprint arXiv:2309.03126

2023/9/6

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers

arXiv preprint arXiv:2308.13191

2023/8/25

Toward fairness in text generation via mutual information minimization based on importance sampling

2023/4/11

Replacing language model for style transfer

arXiv preprint arXiv:2211.07343

2022/11/14

Pengyu Cheng
Pengyu Cheng

H-Index: 6

Waffle: Weight anonymized factorization for federated learning

IEEE Access

2022/5/5

Semi-constraint optimal transport for entity alignment with dangling cases

arXiv preprint arXiv:2203.05744

2022/3/11

Pengyu Cheng
Pengyu Cheng

H-Index: 6

Sheng Yu
Sheng Yu

H-Index: 17

Multiscale visual-attribute co-attention for zero-shot image recognition

IEEE Transactions on Neural Networks and Learning Systems

2021/12/17

Controlled text generation with supervised representation disentanglement and mutual information minimization

2021/6/10

Improving zero-shot voice style transfer via disentangled representation learning

arXiv preprint arXiv:2103.09420

2021/3/17

Pengyu Cheng
Pengyu Cheng

H-Index: 6

Lawrence Carin
Lawrence Carin

H-Index: 63

FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

arXiv preprint arXiv:2103.06413

2021/3/11

Improving Natural Language Understanding via Contrastive Learning Methods

2021

Pengyu Cheng
Pengyu Cheng

H-Index: 6

CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information

2020/11/21

Estimating total correlation with mutual information bounds

2023/4/11

Improving Disentangled Text Representation Learning with Information-Theoretic Guidance

2020

Dynamic Embedding on Textual Networks via a Gaussian Process

Proceedings of the AAAI Conference on Artificial Intelligence

2020/4/3

See List of Professors in Pengyu Cheng University(Duke University)

Co-Authors

academic-engine