no code implementations • 24 Apr 2024 • Dongryeol Lee, Minwoo Lee, Kyungmin Min, Joonsuk Park, Kyomin Jung
Recently, directly using large language models (LLMs) has been shown to be the most reliable method to evaluate QA models.
1 code implementation • 28 Mar 2024 • Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Pu Wang, Minwoo Lee, Srijan Das, Chen Chen
To address these challenges, we propose Bidirectional Autoregressive Motion Model (BAMM), a novel text-to-motion generation framework.
no code implementations • 10 Feb 2024 • Hyukhun Koh, Dohyung Kim, Minwoo Lee, Kyomin Jung
In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to discern the existence of toxicity in the generated text.
no code implementations • 8 Feb 2024 • Kelly Payette, Céline Steger, Roxane Licandro, Priscille de Dumast, Hongwei Bran Li, Matthew Barkovich, Liu Li, Maik Dannecker, Chen Chen, Cheng Ouyang, Niccolò McConnell, Alina Miron, Yongmin Li, Alena Uus, Irina Grigorescu, Paula Ramirez Gilliland, Md Mahfuzur Rahman Siddiquee, Daguang Xu, Andriy Myronenko, Haoyu Wang, Ziyan Huang, Jin Ye, Mireia Alenyà, Valentin Comte, Oscar Camara, Jean-Baptiste Masson, Astrid Nilsson, Charlotte Godard, Moona Mazher, Abdul Qayyum, Yibo Gao, Hangqi Zhou, Shangqi Gao, Jia Fu, Guiming Dong, Guotai Wang, ZunHyan Rieu, HyeonSik Yang, Minwoo Lee, Szymon Płotka, Michal K. Grzeszczyk, Arkadiusz Sitek, Luisa Vargas Daza, Santiago Usma, Pablo Arbelaez, Wenying Lu, WenHao Zhang, Jing Liang, Romain Valabregue, Anand A. Joshi, Krishna N. Nayak, Richard M. Leahy, Luca Wilhelmi, Aline Dändliker, Hui Ji, Antonio G. Gennari, Anton Jakovčić, Melita Klaić, Ana Adžić, Pavel Marković, Gracia Grabarić, Gregor Kasprian, Gregor Dovjak, Milan Rados, Lana Vasung, Meritxell Bach Cuadra, Andras Jakab
The FeTA Challenge 2022 was able to successfully evaluate and advance generalizability of multi-class fetal brain tissue segmentation algorithms for MRI and it continues to benchmark new algorithms.
1 code implementation • 6 Dec 2023 • Ekkasit Pinyoanuntapong, Pu Wang, Minwoo Lee, Chen Chen
MMM consists of two key components: (1) a motion tokenizer that transforms 3D human motion into a sequence of discrete tokens in latent space, and (2) a conditional masked motion transformer that learns to predict randomly masked motion tokens, conditioned on the pre-computed text tokens.
Ranked #5 on Motion Synthesis on KIT Motion-Language
no code implementations • 23 May 2023 • Minwoo Lee, Hyukhun Koh, Kang-il Lee, Dongdong Zhang, Minsung Kim, Kyomin Jung
In this paper, we specifically target the gender bias issue of multilingual machine translation models for unambiguous cases where there is a single correct translation, and propose a bias mitigation method based on a novel approach.
1 code implementation • 23 May 2023 • Dongryeol Lee, Segwang Kim, Minwoo Lee, Hwanhee Lee, Joonsuk Park, Sang-Woo Lee, Kyomin Jung
We first present CAMBIGNQ, a dataset consisting of 5, 654 ambiguous questions, each with relevant passages, possible answers, and a clarification question.
no code implementations • 4 May 2023 • Minwoo Lee, Kyu Tae Kim, Jongho Park
From the drift and diffusion terms of the Fokker--Planck equation, unknown parameters of the system are identified.
1 code implementation • 31 Jan 2023 • Ekkasit Pinyoanuntapong, Ayman Ali, Kalvik Jakkala, Pu Wang, Minwoo Lee, Qucheng Peng, Chen Chen, Zhi Sun
mmWave radar-based gait recognition is a novel user identification method that captures human gait biometrics from mmWave radar return signals.
no code implementations • 16 Jan 2023 • Benjamin Poole, Minwoo Lee
Brain-Computer Interfaces (BCI) have allowed for direct communication from the brain to external applications for the automatic detection of cognitive processes such as error recognition.
1 code implementation • 27 Oct 2022 • Ekkasit Pinyoanuntapong, Ayman Ali, Pu Wang, Minwoo Lee, Chen Chen
Most existing gait recognition methods are appearance-based, which rely on the silhouettes extracted from the video data of human walking activities.
Ranked #6 on Multiview Gait Recognition on CASIA-B
1 code implementation • 10 May 2022 • Archit Parnami, Muhammad Usama, Liyue Fan, Minwoo Lee
Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains.
no code implementations • 7 Mar 2022 • Archit Parnami, Minwoo Lee
Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples.
no code implementations • 2 Dec 2021 • Benjamin Poole, Minwoo Lee
Reinforcement learning (RL) and brain-computer interfaces (BCI) have experienced significant growth over the past decade.
1 code implementation • CVPR 2022 • Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen
To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.
1 code implementation • 17 Nov 2021 • Archit Parnami, Mayuri Deshpande, Anant Kumar Mishra, Minwoo Lee
Two techniques which we focus on in this work are 1) node embeddings from random walk based methods and 2) knowledge graph embeddings.
no code implementations • 18 Oct 2021 • Pinyarash Pinyoanuntapong, Tagore Pothuneedi, Ravikumar Balakrishnan, Minwoo Lee, Chen Chen, Pu Wang
Federated Learning (FL) over wireless multi-hop edge computing networks, i. e., multi-hop FL, is a cost-effective distributed on-device deep learning paradigm.
no code implementations • 14 Oct 2021 • Pinyarash Pinyoanuntapong, Prabhu Janakaraj, Ravikumar Balakrishnan, Minwoo Lee, Chen Chen, Pu Wang
To solve such MDP, multi-agent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i. e., workers) and the remote server.
1 code implementation • 30 Sep 2021 • Minwoo Lee, Seungpil Won, Juae Kim, Hwanhee Lee, Cheoneum Park, Kyomin Jung
Specifically, we employ a two-stage augmentation pipeline to generate new claims and evidences from existing samples.
1 code implementation • 14 May 2021 • Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen
MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.
no code implementations • 13 Dec 2020 • Giang Dao, Minwoo Lee
Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn.
1 code implementation • arXiv 2020 • Archit Parnami, Minwoo Lee
Recognizing a particular command or a keyword, keyword spotting has been widely used in many voice interfaces such as Amazon's Alexa and Google Home.
no code implementations • 1 Apr 2020 • Heeyoung Kwak, Minwoo Lee, Seunghyun Yoon, Jooyoung Chang, Sangmin Park, Kyomin Jung
In this study, we develop a novel graph-based framework for ADR signal detection using healthcare claims data.
1 code implementation • 25 Jul 2019 • Byunghyun Ban, Donghun Ryu, Minwoo Lee
Once a readjustment model is established, application on ISE data can be done in real time.
no code implementations • WS 2019 • Ketki Savle, Wlodek Zadrozny, Minwoo Lee
In this paper we present new results on applying topological data analysis to discourse structures.