Zobrazeno 1 - 10
of 173
pro vyhledávání: '"Yin Xuwang"'
Autor:
Ren, Richard, Basart, Steven, Khoja, Adam, Gatti, Alice, Phan, Long, Yin, Xuwang, Mazeika, Mantas, Pan, Alexander, Mukobi, Gabriel, Kim, Ryan H., Fitz, Stephen, Hendrycks, Dan
As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI safety remains poorly defined and inconsistently measured, leading to con
Externí odkaz:
http://arxiv.org/abs/2407.21792
Autor:
Mazeika, Mantas, Phan, Long, Yin, Xuwang, Zou, Andy, Wang, Zifan, Mu, Norman, Sakhaee, Elham, Li, Nathaniel, Basart, Steven, Li, Bo, Forsyth, David, Hendrycks, Dan
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods. To ad
Externí odkaz:
http://arxiv.org/abs/2402.04249
Autor:
Yin, Xuwang
Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This work propose
Externí odkaz:
http://arxiv.org/abs/2311.06771
Autor:
Zou, Andy, Phan, Long, Chen, Sarah, Campbell, James, Guo, Phillip, Ren, Richard, Pan, Alexander, Yin, Xuwang, Mazeika, Mantas, Dombrowski, Ann-Kathrin, Goel, Shashwat, Li, Nathaniel, Byun, Michael J., Wang, Zifan, Mallen, Alex, Basart, Steven, Koyejo, Sanmi, Song, Dawn, Fredrikson, Matt, Kolter, J. Zico, Hendrycks, Dan
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level representatio
Externí odkaz:
http://arxiv.org/abs/2310.01405
Autor:
Yin, Xuwang
Training adversarially robust discriminative (i.e., softmax) classifier has been the dominant approach to robust classification. Building on recent work on adversarial training (AT)-based generative models, we investigate using AT to learn unnormaliz
Externí odkaz:
http://arxiv.org/abs/2212.07283
Autor:
Ma, Jixin1 (AUTHOR) 17741857967@163.com, Yin, Xuwang1 (AUTHOR) yinxuwang@dlou.edu.cn, Liu, Gang1 (AUTHOR) yinxuwang@dlou.edu.cn, Song, Jinxi2 (AUTHOR) jinxisong@nwu.edu.cn
Publikováno v:
Diversity (14242818). Sep2024, Vol. 16 Issue 9, p513. 23p.
Autor:
Rubaiyat, Abu Hasnat Mohammad, Li, Shiying, Yin, Xuwang, Rabbi, Mohammad Shifat E, Zhuang, Yan, Rohde, Gustavo K.
This paper presents a new end-to-end signal classification method using the signed cumulative distribution transform (SCDT). We adopt a transport-based generative model to define the classification problem. We then make use of mathematical properties
Externí odkaz:
http://arxiv.org/abs/2205.00348
Autor:
Zhuang, Yan, Li, Shiying, Shifat-E-Rabbi, Mohammad, Yin, Xuwang, Rubaiyat, Abu Hasnat Mohammad, Rohde, Gustavo K.
We present a new method for face recognition from digital images acquired under varying illumination conditions. The method is based on mathematical modeling of local gradient distributions using the Radon Cumulative Distribution Transform (R-CDT). W
Externí odkaz:
http://arxiv.org/abs/2202.10642
Autor:
Rabbi, Mohammad Shifat E, Zhuang, Yan, Li, Shiying, Rubaiyat, Abu Hasnat Mohammad, Yin, Xuwang, Rohde, Gustavo K.
Deep convolutional neural networks (CNNs) are broadly considered to be state-of-the-art generic end-to-end image classification systems. However, they are known to underperform when training data are limited and thus require data augmentation strateg
Externí odkaz:
http://arxiv.org/abs/2201.02980
We study a new approach to learning energy-based models (EBMs) based on adversarial training (AT). We show that (binary) AT learns a special kind of energy function that models the support of the data distribution, and the learning process is closely
Externí odkaz:
http://arxiv.org/abs/2012.06568