Publications

Alignment for Large Language Model

Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Jifan Zhang∗, Lalit Jain∗, Yang Guo∗, Jiayi Chen, Kuan Lok Zhou, Siddharth Suresh, Andrew Wagenmaker, Scott Sievert, Timothy Rogers, Kevin Jamieson, Robert Mankoff, Robert Nowak
Submitted to Neural Information Processing Systems (Neurips) 2024 Datasets & Benchmarks
[arXiv] [code] [dataset]

Adversarial Robustness for Model Adaptation

Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
Nils Palumbo*, Yang Guo*, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha
International Conference on Machine Learning (ICML), 2024
[paper] [code]

Towards Evaluating the Robustness of Neural Networks Learned by Transduction
Jiefeng Chen, Xi Wu, Yang Guo, Yingyu Liang, and Somesh Jha
International Conference on Learning Representations (ICLR), 2022
[paper][code]

Best of Both Worlds: Towards Adversarial Robustness with Transduction and Rejection
Nils Palumbo*, Yang Guo*, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha
ML Safety Workshop, Neural Information Processing Systems (Neurips) 2022
[paper]

Memory-Efficient Tensor Decomposition

Low-rank tucker approximation of a tensor from streaming data
Yiming Sun, Yang Guo, Charlene Luo, Joel Tropp, and Madeleine Udell
SIAM Journal on Mathematics of Data Science 2 (4), 1123-1150
[paper] [code]

Tensor random projection for low memory dimension reduction
Yang Guo*, Yiming Sun*, Joel Tropp, and Madeleine Udell
Relational Representation Learning Workshop, Neural Information Processing Systems (Neurips), 2018
[paper]

Manuscripts

Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation
Xi Wu, Yang Guo, Jiefeng Chen, Yingyu Liang, Somesh Jha, and Prasad Chalasani
Manuscript
[arXiv]