activity
20212023
most citedImproving Bot Response Contradiction Detection via Utterance Rewriting

1 citations · 1 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CL20235 cited

Certified Robustness for Large Language Models with Self-Denoising

Zhen Zhang, Guanhua Zhang, Bairu Hou +5

Although large language models (LLMs) have achieved great success in vast real-world applications, their vulnerabilities towards noisy inputs have significantly limited their uses,…

cs.LG2023

Fairness Improves Learning from Noisily Labeled Long-Tailed Data

Jiaheng Wei, Zhaowei Zhu, Gang Niu +4

Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning. Most prior works treat either problem in an i…

eess.IV2023

SMUG: Towards robust MRI reconstruction by smoothed unrolling

Hui Li, Jinghan Jia, Shijun Liang +3

Although deep learning (DL) has gained much popularity for accelerated magnetic resonance imaging (MRI), recent studies have shown that DL-based MRI reconstruction models could be…

cs.LG2023

Certified Interpretability Robustness for Class Activation Mapping

Alex Gu, Tsui-Wei Weng, Pin-Yu Chen +2

Interpreting machine learning models is challenging but crucial for ensuring the safety of deep networks in autonomous driving systems. Due to the prevalence of deep learning based…

cs.LG2023

Towards Understanding How Self-training Tolerates Data Backdoor Poisoning

Soumyadeep Pal, Ren Wang, Yuguang Yao +1

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poison…

cs.CV2023

Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning

Kanghao Chen, Sijia Liu, Ruixuan Wang +1

Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often f…