110 citations · 336 across the 32 of their papers we have counts for
32 papers
Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech
Semin Kim, Seungjun Chung, Taehong Moon +8
Recent advances in text-to-speech (TTS) models show impressive speech naturalness and quality, yet the role of large-scale open data in driving this progress remains underexplored.…
Buffer-based Gradient Projection for Continual Federated Learning
Shenghong Dai, Jy-yong Sohn, Yicong Chen +5
Continual Federated Learning (CFL) is essential for enabling real-world applications where multiple decentralized clients adaptively learn from continuous data streams. A significa…
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning
Joonyoung Kim, Kangwook Lee, Haebin Shin +5
The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short, and there are just too…
Teaching Arithmetic to Small Transformers
Nayoung Lee, Kartik Sreenivasan, Jason D. Lee +2
Large language models like GPT-4 exhibit emergent capabilities across general-purpose tasks, such as basic arithmetic, when trained on extensive text data, even though these tasks…
Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding
Seongjun Yang, Gibbeum Lee, Jaewoong Cho +2
This paper presents "Predictive Pipelined Decoding (PPD)," an approach that speeds up greedy decoding in Large Language Models (LLMs) while maintaining the exact same output as the…
Prompted LLMs as Chatbot Modules for Long Open-domain Conversation
Gibbeum Lee, Volker Hartmann, Jongho Park +2
In this paper, we propose MPC (Modular Prompted Chatbot), a new approach for creating high-quality conversational agents without the need for fine-tuning. Our method utilizes pre-t…
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
Joseph Shenouda, Rahul Parhi, Kangwook Lee +1
This paper introduces a novel theoretical framework for the analysis of vector-valued neural networks through the development of vector-valued variation spaces, a new class of repr…
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
Ying Fan, Olivia Watkins, Yuqing Du +7
Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and the…
Improving Fair Training under Correlation Shifts
Yuji Roh, Kangwook Lee, Steven Euijong Whang +1
Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data di…
Looped Transformers as Programmable Computers
Angeliki Giannou, Shashank Rajput, Jy-yong Sohn +3
We present a framework for using transformer networks as universal computers by programming them with specific weights and placing them in a loop. Our input sequence acts as a punc…
Optimizing DDPM Sampling with Shortcut Fine-Tuning
Ying Fan, Kangwook Lee
In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs). S…
Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Dohyun Kwon, Ying Fan, Kangwook Lee
Score-based generative models are shown to achieve remarkable empirical performances in various applications such as image generation and audio synthesis. However, a theoretical un…
Outlier-Robust Group Inference via Gradient Space Clustering
Yuchen Zeng, Kristjan Greenewald, Kangwook Lee +2
Traditional machine learning models focus on achieving good performance on the overall training distribution, but they often underperform on minority groups. Existing methods can i…
PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks
Liu Yang, Jifan Zhang, Joseph Shenouda +3
Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective drivin…
LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks
Tuan Dinh, Yuchen Zeng, Ruisu Zhang +6
Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language do…
Breaking Fair Binary Classification with Optimal Flipping Attacks
Changhun Jo, Jy-yong Sohn, Kangwook Lee
Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the…
Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
Tuan Dinh, Jy-yong Sohn, Shashank Rajput +5
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods. Recent findings have shown that the accuracy and robustness of unsupe…
Improved Input Reprogramming for GAN Conditioning
Tuan Dinh, Daewon Seo, Zhixu Du +2
We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approa…
Rare Gems: Finding Lottery Tickets at Initialization
Kartik Sreenivasan, Jy-yong Sohn, Liu Yang +6
Large neural networks can be pruned to a small fraction of their original size, with little loss in accuracy, by following a time-consuming "train, prune, re-train" approach. Frank…
GenLabel: Mixup Relabeling using Generative Models
Jy-yong Sohn, Liang Shang, Hongxu Chen +3
Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades…
Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
Youngjune Lee, Oh Joon Kwon, Haeju Lee +3
Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to addre…
Gradient Inversion with Generative Image Prior
Jinwoo Jeon, Jaechang Kim, Kangwook Lee +2
Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients devices to preserve privacy, and the server trains models on the data via…
Sample Selection for Fair and Robust Training
Yuji Roh, Kangwook Lee, Steven Euijong Whang +1
Fairness and robustness are critical elements of Trustworthy AI that need to be addressed together. Fairness is about learning an unbiased model while robustness is about learning…
Improving Fairness via Federated Learning
Yuchen Zeng, Hongxu Chen, Kangwook Lee
Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First, is f…