1 code implementation • 27 Sep 2024 • Jaepill Choi, Kyubyung Chae, Jiwoo Song, Yohan Jo, Taesup Kim
In this work, we introduce a novel and straightforward approach called Model-based Preference Optimization (MPO) to fine-tune LLMs for improved summarization abilities without any human feedback.
no code implementations • 17 Jul 2024 • Donggeun Kim, Taesup Kim
This framework enables the model to predict the embedding of a missing modality in the representation space during inference.
1 code implementation • 15 Apr 2024 • Kyubyung Chae, Jaepill Choi, Yohan Jo, Taesup Kim
We hypothesize that the domain (or topic) of the source text triggers the model to generate text that is highly probable in the domain, neglecting the details of the source text.
no code implementations • 8 Mar 2024 • Jinha Park, Wonguk Cho, Taesup Kim
In this paper, we address a representative case of data inequality problem across domains termed Semi-Supervised Domain Generalization (SSDG), in which only one domain is labeled while the rest are unlabeled.
no code implementations • 29 Jan 2024 • Namju Kwak, Taesup Kim
Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile.
1 code implementation • CVPR 2023 • Suhyun Kang, Duhun Hwang, Moonjung Eo, Taesup Kim, Wonjong Rhee
In this study, we propose Geometry-Adaptive Preconditioned gradient descent (GAP) that can overcome the limitations in MAML; GAP can efficiently meta-learn a preconditioner that is dependent on task-specific parameters, and its preconditioner can be shown to be a Riemannian metric.
no code implementations • ICCV 2023 • Wonguk Cho, Jinha Park, Taesup Kim
In this paper, we propose Complementary Domain Adaptation and Generalization (CoDAG), a simple yet effective learning framework that combines domain adaptation and generalization in a complementary manner to achieve three major goals of unsupervised continual domain shift learning: adapting to a current domain, generalizing to unseen domains, and preventing forgetting of previously seen domains.
Ranked #1 on Unsupervised Continual Domain Shift Learning on PACS
Domain Generalization Unsupervised Continual Domain Shift Learning +1
1 code implementation • 28 Feb 2023 • Minchang Kim, Yongjin Yang, Jung Hyun Ryu, Taesup Kim
To alleviate this limitation, we propose a novel sequential recommendation framework based on gradient-based meta-learning that captures the imbalanced rating distribution of each user and computes adaptive loss for user-specific learning.
2 code implementations • 28 May 2022 • Massimo Caccia, Jonas Mueller, Taesup Kim, Laurent Charlin, Rasool Fakoor
We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitigate the effects of catastrophic forgetting.
1 code implementation • 10 Dec 2021 • Kavosh Asadi, Rasool Fakoor, Omer Gottesman, Taesup Kim, Michael L. Littman, Alexander J. Smola
In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates that incentivize the online network to remain in the proximity of the target network.
1 code implementation • 26 Feb 2021 • Rasool Fakoor, Taesup Kim, Jonas Mueller, Alexander J. Smola, Ryan J. Tibshirani
Quantile regression is a fundamental problem in statistical learning motivated by a need to quantify uncertainty in predictions, or to model a diverse population without being overly reductive.
no code implementations • 26 Aug 2020 • Taesup Kim, Sungwoong Kim, Yoshua Bengio
It approximates sparsely connected networks by explicitly defining multiple branches to simultaneously learn representations with different visual concepts or properties.
2 code implementations • NeurIPS 2019 • Taesup Kim, Sungjin Ahn, Yoshua Bengio
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data.
no code implementations • 13 Jun 2019 • Sungwoong Kim, Ildoo Kim, Sungbin Lim, Woonhyuk Baek, Chiheon Kim, Hyungjoo Cho, Boogeon Yoon, Taesup Kim
In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image segmentation, to automatically optimize a neural architecture from a large design space.
4 code implementations • CVPR 2019 • Jongmin Kim, Taesup Kim, Sungwoong Kim, Chang D. Yoo
In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning.
11 code implementations • NeurIPS 2019 • Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim, Sungwoong Kim
Data augmentation is an essential technique for improving generalization ability of deep learning models.
Ranked #2 on Image Classification on SVHN
2 code implementations • NeurIPS 2018 • Taesup Kim, Jaesik Yoon, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem.
no code implementations • 20 Jan 2018 • Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeswar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition.
1 code implementation • ICLR 2018 • Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models.
no code implementations • 7 Sep 2017 • Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeshwar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio
By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble.
no code implementations • 19 Jul 2017 • Taesup Kim, Inchul Song, Yoshua Bengio
Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability.
no code implementations • 10 Jun 2016 • Taesup Kim, Yoshua Bengio
Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distribution in the inner loop of training.