Search Results for author: Taesup Kim

Found 22 papers, 12 papers with code

Model-based Preference Optimization in Abstractive Summarization without Human Feedback

1 code implementation27 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.

Abstractive Text Summarization

Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models

no code implementations17 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.

parameter-efficient fine-tuning

Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information

1 code implementation15 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.

Abstractive Text Summarization Hallucination

Overcoming Data Inequality across Domains with Semi-Supervised Domain Generalization

no code implementations8 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.

Domain Generalization Semi-Supervised Domain Generalization

X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios

no code implementations29 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.

Language Modelling parameter-efficient fine-tuning

Meta-Learning with a Geometry-Adaptive Preconditioner

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.

Few-Shot Image Classification Few-Shot Learning

Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning

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.

Domain Generalization Unsupervised Continual Domain Shift Learning +1

Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation

1 code implementation28 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.

Few-Shot Learning Sequential Recommendation

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

2 code implementations28 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.

Continual Learning Continuous Control +4

Faster Deep Reinforcement Learning with Slower Online Network

1 code implementation10 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.

reinforcement-learning Reinforcement Learning +1

Flexible Model Aggregation for Quantile Regression

1 code implementation26 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.

Econometrics Prediction Intervals +1

Visual Concept Reasoning Networks

no code implementations26 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.

Action Recognition Image Classification +4

Variational Temporal Abstraction

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.

Scalable Neural Architecture Search for 3D Medical Image Segmentation

no code implementations13 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.

Decoder Image Segmentation +4

Edge-labeling Graph Neural Network for Few-shot Learning

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.

Clustering Few-Shot Image Classification +2

Fast AutoAugment

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.

Image Augmentation Image Classification

Bayesian Model-Agnostic Meta-Learning

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.

Active Learning Image Classification +3

PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples

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.

Two-sample testing

Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition

no code implementations19 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.

speech-recognition Speech Recognition

Deep Directed Generative Models with Energy-Based Probability Estimation

no code implementations10 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.