no code implementations • 4 Apr 2024 • Jooyoung Lee, Fan Yang, Thanh Tran, Qian Hu, Emre Barut, Kai-Wei Chang, Chengwei Su
The Frozen large LM is then prompted to predict a task output based on the rationale generated by the lightweight LM.
no code implementations • 13 Mar 2024 • Jooyoung Lee, Emily Booth, Hany Farid, Marian-Andrei Rizoiu
What if misinformation is not an information problem at all?
no code implementations • 8 Nov 2023 • Eiji Yamamoto, Keehyoung Joo, Jooyoung Lee, Mark S. P. Sansom, Masato Yasui
Moreover, we demonstrate the pH-sensing mechanism in which the protonation of H184 and H189 under low pH conditions allosterically triggers the gating of the SF region.
1 code implementation • 24 Oct 2023 • Jason Lucas, Adaku Uchendu, Michiharu Yamashita, Jooyoung Lee, Shaurya Rohatgi, Dongwon Lee
Recent ubiquity and disruptive impacts of large language models (LLMs) have raised concerns about their potential to be misused (. i. e, generating large-scale harmful and misleading content).
no code implementations • ICCV 2023 • Jongmin Park, Jooyoung Lee, Munchurl Kim
Recently, neural network (NN)-based image compression studies have actively been made and has shown impressive performance in comparison to traditional methods.
no code implementations • 29 Jun 2023 • Yeongwoong Kim, Hyewon Jeong, Janghyun Yu, Younhee Kim, Jooyoung Lee, Se Yoon Jeong, Hui Yong Kim
In the feature compression track of MPEG-VCM, multi-scale features extracted from images are subject to compression.
1 code implementation • 19 Jun 2023 • Eun Jung Yeo, Hyungshin Ryu, Jooyoung Lee, Sunhee Kim, Minhwa Chung
This paper presents a large-scale analysis of L2 Korean pronunciation error patterns from five different language backgrounds, Chinese, Vietnamese, Japanese, Thai, and English, by using automatic phonetic transcription.
2 code implementations • 3 Apr 2023 • Adaku Uchendu, Jooyoung Lee, Hua Shen, Thai Le, Ting-Hao 'Kenneth' Huang, Dongwon Lee
Advances in Large Language Models (e. g., GPT-4, LLaMA) have improved the generation of coherent sentences resembling human writing on a large scale, resulting in the creation of so-called deepfake texts.
1 code implementation • 8 Nov 2022 • Jooyoung Lee, Seyoon Jeong, Munchurl Kim
For this, we first generate a 3D importance map as the nature of input content to represent the underlying importance of the representation elements.
1 code implementation • Findings (ACL) 2022 • Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, Dongwon Lee
We find that adversarial texts generated by ANTHRO achieve the best trade-off between (1) attack success rate, (2) semantic preservation of the original text, and (3) stealthiness--i. e. indistinguishable from human writings hence harder to be flagged as suspicious.
1 code implementation • 15 Mar 2022 • Jooyoung Lee, Thai Le, Jinghui Chen, Dongwon Lee
Our results suggest that (1) three types of plagiarism widely exist in LMs beyond memorization, (2) both size and decoding methods of LMs are strongly associated with the degrees of plagiarism they exhibit, and (3) fine-tuned LMs' plagiarism patterns vary based on their corpus similarity and homogeneity.
1 code implementation • 30 Dec 2019 • Jooyoung Lee, Seunghyun Cho, Munchurl Kim
In order to show the effectiveness of our proposed JointIQ-Net, extensive experiments have been performed, and showed that the JointIQ-Net achieves a remarkable performance improvement in coding efficiency in terms of both PSNR and MS-SSIM, compared to the previous learned image compression methods and the conventional codecs such as VVC Intra (VTM 7. 1), BPG, and JPEG2000.
no code implementations • 19 Jan 2019 • Vivek Kumar, Manuel Mazzara, Maj. Gen., Angelo Messina, Jooyoung Lee
Terrorism has become one of the most tedious problems to deal with and a prominent threat to mankind.
2 code implementations • ICLR 2019 • Jooyoung Lee, Seunghyun Cho, Seung-Kwon Beack
We propose a context-adaptive entropy model for use in end-to-end optimized image compression.
no code implementations • 5 Sep 2017 • Konstantin Sozykin, Stanislav Protasov, Adil Khan, Rasheed Hussain, Jooyoung Lee
Automatic analysis of the video is one of most complex problems in the fields of computer vision and machine learning.
no code implementations • 16 Jun 2017 • Leonard Johard, Victor Rivera, Manuel Mazzara, Jooyoung Lee
In this paper we propose an algorithm, Simple Hebbian PCA, and prove that it is able to calculate the principal component analysis (PCA) in a distributed fashion across nodes.