المؤلفون: Jang, Youngdong, Lee, Dong In, Jang, MinHyuk, Kim, Jong Wook, Yang, Feng, Kim, Sangpil

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing

الوصف: The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the pivotal solutions for safely deploying NeRF-based 3D representations. However, existing methods are designed to apply only to implicit or explicit NeRF representations. In this work, we introduce an innovative watermarking method that can be employed in both representations of NeRF. This is achieved by fine-tuning NeRF to embed binary messages in the rendering process. In detail, we propose utilizing the discrete wavelet transform in the NeRF space for watermarking. Furthermore, we adopt a deferred back-propagation technique and introduce a combination with the patch-wise loss to improve rendering quality and bit accuracy with minimum trade-offs. We evaluate our method in three different aspects: capacity, invisibility, and robustness of the embedded watermarks in the 2D-rendered images. Our method achieves state-of-the-art performance with faster training speed over the compared state-of-the-art methods.

الوصول الحر: http://arxiv.org/abs/2405.02066Test

المؤلفون: Jang, Beakcheol, Kim, Inhwan, Kim, Jong Wook

المصدر: JMIR Medical Informatics, Vol 9, Iss 5, p e23305 (2021)

مصطلحات موضوعية: Computer applications to medicine. Medical informatics, R858-859.7

الوصف: BackgroundEach year, influenza affects 3 to 5 million people and causes 290,000 to 650,000 fatalities worldwide. To reduce the fatalities caused by influenza, several countries have established influenza surveillance systems to collect early warning data. However, proper and timely warnings are hindered by a 1- to 2-week delay between the actual disease outbreaks and the publication of surveillance data. To address the issue, novel methods for influenza surveillance and prediction using real-time internet data (such as search queries, microblogging, and news) have been proposed. Some of the currently popular approaches extract online data and use machine learning to predict influenza occurrences in a classification mode. However, many of these methods extract training data subjectively, and it is difficult to capture the latent characteristics of the data correctly. There is a critical need to devise new approaches that focus on extracting training data by reflecting the latent characteristics of the data. ObjectiveIn this paper, we propose an effective method to extract training data in a manner that reflects the hidden features and improves the performance by filtering and selecting only the keywords related to influenza before the prediction. MethodsAlthough word embedding provides a distributed representation of words by encoding the hidden relationships between various tokens, we enhanced the word embeddings by selecting keywords related to the influenza outbreak and sorting the extracted keywords using the Pearson correlation coefficient in order to solely keep the tokens with high correlation with the actual influenza outbreak. The keyword extraction process was followed by a predictive model based on long short-term memory that predicts the influenza outbreak. To assess the performance of the proposed predictive model, we used and compared a variety of word embedding techniques. ResultsWord embedding without our proposed sorting process showed 0.8705 prediction accuracy when 50.2 keywords were selected on average. Conversely, word embedding using our proposed sorting process showed 0.8868 prediction accuracy and an improvement in prediction accuracy of 12.6%, although smaller amounts of training data were selected, with only 20.6 keywords on average. ConclusionsThe sorting stage empowers the embedding process, which improves the feature extraction process because it acts as a knowledge base for the prediction component. The model outperformed other current approaches that use flat extraction before prediction.

وصف الملف: electronic resource

العلاقة: https://medinform.jmir.org/2021/5/e23305Test; https://doaj.org/toc/2291-9694Test

الوصول الحر: https://doaj.org/article/ae45c4960630467ca66ce30385ce58a2Test

المؤلفون: OpenAI, Achiam, Josh, Adler, Steven, Agarwal, Sandhini, Ahmad, Lama, Akkaya, Ilge, Aleman, Florencia Leoni, Almeida, Diogo, Altenschmidt, Janko, Altman, Sam, Anadkat, Shyamal, Avila, Red, Babuschkin, Igor, Balaji, Suchir, Balcom, Valerie, Baltescu, Paul, Bao, Haiming, Bavarian, Mohammad, Belgum, Jeff, Bello, Irwan, Berdine, Jake, Bernadett-Shapiro, Gabriel, Berner, Christopher, Bogdonoff, Lenny, Boiko, Oleg, Boyd, Madelaine, Brakman, Anna-Luisa, Brockman, Greg, Brooks, Tim, Brundage, Miles, Button, Kevin, Cai, Trevor, Campbell, Rosie, Cann, Andrew, Carey, Brittany, Carlson, Chelsea, Carmichael, Rory, Chan, Brooke, Chang, Che, Chantzis, Fotis, Chen, Derek, Chen, Sully, Chen, Ruby, Chen, Jason, Chen, Mark, Chess, Ben, Cho, Chester, Chu, Casey, Chung, Hyung Won, Cummings, Dave, Currier, Jeremiah, Dai, Yunxing, Decareaux, Cory, Degry, Thomas, Deutsch, Noah, Deville, Damien, Dhar, Arka, Dohan, David, Dowling, Steve, Dunning, Sheila, Ecoffet, Adrien, Eleti, Atty, Eloundou, Tyna, Farhi, David, Fedus, Liam, Felix, Niko, Fishman, Simón Posada, Forte, Juston, Fulford, Isabella, Gao, Leo, Georges, Elie, Gibson, Christian, Goel, Vik, Gogineni, Tarun, Goh, Gabriel, Gontijo-Lopes, Rapha, Gordon, Jonathan, Grafstein, Morgan, Gray, Scott, Greene, Ryan, Gross, Joshua, Gu, Shixiang Shane, Guo, Yufei, Hallacy, Chris, Han, Jesse, Harris, Jeff, He, Yuchen, Heaton, Mike, Heidecke, Johannes, Hesse, Chris, Hickey, Alan, Hickey, Wade, Hoeschele, Peter, Houghton, Brandon, Hsu, Kenny, Hu, Shengli, Hu, Xin, Huizinga, Joost, Jain, Shantanu, Jain, Shawn, Jang, Joanne, Jiang, Angela, Jiang, Roger, Jin, Haozhun, Jin, Denny, Jomoto, Shino, Jonn, Billie, Jun, Heewoo, Kaftan, Tomer, Kaiser, Łukasz, Kamali, Ali, Kanitscheider, Ingmar, Keskar, Nitish Shirish, Khan, Tabarak, Kilpatrick, Logan, Kim, Jong Wook, Kim, Christina, Kim, Yongjik, Kirchner, Jan Hendrik, Kiros, Jamie, Knight, Matt, Kokotajlo, Daniel, Kondraciuk, Łukasz, Kondrich, Andrew, Konstantinidis, Aris, Kosic, Kyle, Krueger, Gretchen, Kuo, Vishal, Lampe, Michael, Lan, Ikai, Lee, Teddy, Leike, Jan, Leung, Jade, Levy, Daniel, Li, Chak Ming, Lim, Rachel, Lin, Molly, Lin, Stephanie, Litwin, Mateusz, Lopez, Theresa, Lowe, Ryan, Lue, Patricia, Makanju, Anna, Malfacini, Kim, Manning, Sam, Markov, Todor, Markovski, Yaniv, Martin, Bianca, Mayer, Katie, Mayne, Andrew, McGrew, Bob, McKinney, Scott Mayer, McLeavey, Christine, McMillan, Paul, McNeil, Jake, Medina, David, Mehta, Aalok, Menick, Jacob, Metz, Luke, Mishchenko, Andrey, Mishkin, Pamela, Monaco, Vinnie, Morikawa, Evan, Mossing, Daniel, Mu, Tong, Murati, Mira, Murk, Oleg, Mély, David, Nair, Ashvin, Nakano, Reiichiro, Nayak, Rajeev, Neelakantan, Arvind, Ngo, Richard, Noh, Hyeonwoo, Ouyang, Long, O'Keefe, Cullen, Pachocki, Jakub, Paino, Alex, Palermo, Joe, Pantuliano, Ashley, Parascandolo, Giambattista, Parish, Joel, Parparita, Emy, Passos, Alex, Pavlov, Mikhail, Peng, Andrew, Perelman, Adam, Peres, Filipe de Avila Belbute, Petrov, Michael, Pinto, Henrique Ponde de Oliveira, Michael, Pokorny, Pokrass, Michelle, Pong, Vitchyr H., Powell, Tolly, Power, Alethea, Power, Boris, Proehl, Elizabeth, Puri, Raul, Radford, Alec, Rae, Jack, Ramesh, Aditya, Raymond, Cameron, Real, Francis, Rimbach, Kendra, Ross, Carl, Rotsted, Bob, Roussez, Henri, Ryder, Nick, Saltarelli, Mario, Sanders, Ted, Santurkar, Shibani, Sastry, Girish, Schmidt, Heather, Schnurr, David, Schulman, John, Selsam, Daniel, Sheppard, Kyla, Sherbakov, Toki, Shieh, Jessica, Shoker, Sarah, Shyam, Pranav, Sidor, Szymon, Sigler, Eric, Simens, Maddie, Sitkin, Jordan, Slama, Katarina, Sohl, Ian, Sokolowsky, Benjamin, Song, Yang, Staudacher, Natalie, Such, Felipe Petroski, Summers, Natalie, Sutskever, Ilya, Tang, Jie, Tezak, Nikolas, Thompson, Madeleine B., Tillet, Phil, Tootoonchian, Amin, Tseng, Elizabeth, Tuggle, Preston, Turley, Nick, Tworek, Jerry, Uribe, Juan Felipe Cerón, Vallone, Andrea, Vijayvergiya, Arun, Voss, Chelsea, Wainwright, Carroll, Wang, Justin Jay, Wang, Alvin, Wang, Ben, Ward, Jonathan, Wei, Jason, Weinmann, CJ, Welihinda, Akila, Welinder, Peter, Weng, Jiayi, Weng, Lilian, Wiethoff, Matt, Willner, Dave, Winter, Clemens, Wolrich, Samuel, Wong, Hannah, Workman, Lauren, Wu, Sherwin, Wu, Jeff, Wu, Michael, Xiao, Kai, Xu, Tao, Yoo, Sarah, Yu, Kevin, Yuan, Qiming, Zaremba, Wojciech, Zellers, Rowan, Zhang, Chong, Zhang, Marvin, Zhao, Shengjia, Zheng, Tianhao, Zhuang, Juntang, Zhuk, William, Zoph, Barret

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

الوصف: We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. GPT-4 is a Transformer-based model pre-trained to predict the next token in a document. The post-training alignment process results in improved performance on measures of factuality and adherence to desired behavior. A core component of this project was developing infrastructure and optimization methods that behave predictably across a wide range of scales. This allowed us to accurately predict some aspects of GPT-4's performance based on models trained with no more than 1/1,000th the compute of GPT-4.
Comment: 100 pages; updated authors list; fixed author names and added citation

الوصول الحر: http://arxiv.org/abs/2303.08774Test

المؤلفون: Radford, Alec, Kim, Jong Wook, Xu, Tao, Brockman, Greg, McLeavey, Christine, Sutskever, Ilya

مصطلحات موضوعية: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Sound

الوصف: We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

الوصول الحر: http://arxiv.org/abs/2212.04356Test

المؤلفون: Edemacu, Kennedy, Jang, Beakcheol, Kim, Jong Wook

مصطلحات موضوعية: Computer Science - Cryptography and Security

الوصف: Due to privacy concerns, multi-party gradient tree boosting algorithms have become widely popular amongst machine learning researchers and practitioners. However, limited existing works have focused on vertically partitioned datasets, and the few existing works are either not scalable or tend to leak information. Thus, in this work, we propose SSXGB which is a scalable and secure multi-party gradient tree boosting framework for vertically partitioned datasets with partially outsourced computations. Specifically, we employ an additive homomorphic encryption (HE) scheme for security. We design two sub-protocols based on the HE scheme to perform non-linear operations associated with gradient tree boosting algorithms. Next, we propose a secure training and a secure prediction algorithms under the SSXGB framework. Then we provide theoretical security and communication analysis for the proposed framework. Finally, we evaluate the performance of the framework with experiments using two real-world datasets.

الوصول الحر: http://arxiv.org/abs/2202.03245Test

المؤلفون: Neelakantan, Arvind, Xu, Tao, Puri, Raul, Radford, Alec, Han, Jesse Michael, Tworek, Jerry, Yuan, Qiming, Tezak, Nikolas, Kim, Jong Wook, Hallacy, Chris, Heidecke, Johannes, Shyam, Pranav, Power, Boris, Nekoul, Tyna Eloundou, Sastry, Girish, Krueger, Gretchen, Schnurr, David, Such, Felipe Petroski, Hsu, Kenny, Thompson, Madeleine, Khan, Tabarak, Sherbakov, Toki, Jang, Joanne, Welinder, Peter, Weng, Lilian

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Machine Learning

الوصف: Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and model architecture. In this work, we show that contrastive pre-training on unsupervised data at scale leads to high quality vector representations of text and code. The same unsupervised text embeddings that achieve new state-of-the-art results in linear-probe classification also display impressive semantic search capabilities and sometimes even perform competitively with fine-tuned models. On linear-probe classification accuracy averaging over 7 tasks, our best unsupervised model achieves a relative improvement of 4% and 1.8% over previous best unsupervised and supervised text embedding models respectively. The same text embeddings when evaluated on large-scale semantic search attains a relative improvement of 23.4%, 14.7%, and 10.6% over previous best unsupervised methods on MSMARCO, Natural Questions and TriviaQA benchmarks, respectively. Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20.8% relative improvement over prior best work on code search.

الوصول الحر: http://arxiv.org/abs/2201.10005Test

المؤلفون: Kim, Jong Wook

مرشدي الرسالة: Nevins, Joseph R

مصطلحات موضوعية: Genetics, Systematic biology, cyclin E, E2F, integrative, microRNA, Myc, PTEN

الوصف: Cancer is a disease state that arises as a result of multiple alterations in signaling pathways that are critical for making key cell fate decisions in normal cells. Understanding how these pathways operate under normal circumstances, therefore, is crucial for comprehensive understanding of tumorigenic process. With Myc and E2F pathways being central components for controlling cell proliferation, an important property that defines a cancer cell, as well as expanding roles for microRNAs(miRNA) in control of gene expression, we asked if we may better understand the underlying regulatory (transcription factor, microRNA) structure that contribute to Myc and E2F pathway activities. Through integrative analysis of mRNA and miRNA expression profile, we observe a distinct regulatory pattern in which, in the case of Myc pathway, Myc-induced miRNAs were contributing to the repression of negative regulators of cell cycle, including PTEN, while in case of E2F pathway, E2F-induced miRs were forming an incoherent Feed-Forward Loop(iFFL) with a number of E2F-induced genes including cyclin E. We further demonstrate through functional studies, as well as through single cell imaging of gene expression dynamics that miRNAs, depending on the context of either Myc or E2F pathway, play distinct roles in ensuring that cell fate decisions relevant to these pathways are properly executed.
Dissertation

الإتاحة: http://hdl.handle.net/10161/3813Test

المؤلفون: Wortsman, Mitchell, Ilharco, Gabriel, Kim, Jong Wook, Li, Mike, Kornblith, Simon, Roelofs, Rebecca, Gontijo-Lopes, Raphael, Hajishirzi, Hannaneh, Farhadi, Ali, Namkoong, Hongseok, Schmidt, Ludwig

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

الوصف: Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (i.e., without fine-tuning on a specific dataset). Although existing fine-tuning methods substantially improve accuracy on a given target distribution, they often reduce robustness to distribution shifts. We address this tension by introducing a simple and effective method for improving robustness while fine-tuning: ensembling the weights of the zero-shot and fine-tuned models (WiSE-FT). Compared to standard fine-tuning, WiSE-FT provides large accuracy improvements under distribution shift, while preserving high accuracy on the target distribution. On ImageNet and five derived distribution shifts, WiSE-FT improves accuracy under distribution shift by 4 to 6 percentage points (pp) over prior work while increasing ImageNet accuracy by 1.6 pp. WiSE-FT achieves similarly large robustness gains (2 to 23 pp) on a diverse set of six further distribution shifts, and accuracy gains of 0.8 to 3.3 pp compared to standard fine-tuning on seven commonly used transfer learning datasets. These improvements come at no additional computational cost during fine-tuning or inference.
Comment: CVPR 2022

الوصول الحر: http://arxiv.org/abs/2109.01903Test

المؤلفون: Agarwal, Sandhini, Krueger, Gretchen, Clark, Jack, Radford, Alec, Kim, Jong Wook, Brundage, Miles

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Computers and Society

الوصف: Recently, there have been breakthroughs in computer vision ("CV") models that are more generalizable with the advent of models such as CLIP and ALIGN. In this paper, we analyze CLIP and highlight some of the challenges such models pose. CLIP reduces the need for task specific training data, potentially opening up many niche tasks to automation. CLIP also allows its users to flexibly specify image classification classes in natural language, which we find can shift how biases manifest. Additionally, through some preliminary probes we find that CLIP can inherit biases found in prior computer vision systems. Given the wide and unpredictable domain of uses for such models, this raises questions regarding what sufficiently safe behaviour for such systems may look like. These results add evidence to the growing body of work calling for a change in the notion of a 'better' model--to move beyond simply looking at higher accuracy at task-oriented capability evaluations, and towards a broader 'better' that takes into account deployment-critical features such as different use contexts, and people who interact with the model when thinking about model deployment.
Comment: arXiv admin note: substantial text overlap with arXiv:2103.00020

الوصول الحر: http://arxiv.org/abs/2108.02818Test

المؤلفون: Ryu, Seo-Yoon, Cheong, Cheolung, Kim, Jong Wook, Park, Byung Il

المساهمون: Ministry of Education, National Research Foundation of Korea

المصدر: Results in Engineering ; volume 21, page 101857 ; ISSN 2590-1230

مصطلحات موضوعية: General Engineering

الإتاحة: https://doi.org/10.1016/j.rineng.2024.101857Test
https://api.elsevier.com/content/article/PII:S2590123024001105?httpAccept=text/xmlTest
https://api.elsevier.com/content/article/PII:S2590123024001105?httpAccept=text/plainTest