Taesub YUN

GeunHo LEE

Dongjun KIM

JoonHo JANG

Seungjae SHIN

Yunkyeong SEO

Muhyun BYUN

Youngjae CHO

Kwanghyeon LEE

Juho CHOI

Mingi JI

Weonyoung JOO

Yoon-Yeong KIM

Dohyung KIM

Kyungwoo SONG

Su-Jin SHIN

Sungrae PARK

Jang Won BAE

Wonsung LEE

Yeodong YOUN

Sungeun KIM

Hyun SAGONG

Jeahoon LEE

Yongjin SHIN

Kyu Seok KIM

Hyemi KIM

Minjae JUNG

JunKeon PARK

Kiung KIM

Do-Hyeong KIM

Doosup CHOI

Doyun KIM

Chi-jung JUNG

Junseok LEE

Ah-Ram KANG

Sehoon LEE

Hyeonmin LEE

Rosy OH

Yun-Gyung GONG

Eun-Soon SHIN

Jong-Mu KIM

Keen-Il YOUK

Junghyun AHN

Jeong Hee HONG

Applied Artificial Intelligence Laboratory at KAIST. The lab focuses on Deep Generative Model and Probabilistic Graphical Model.

카이스트 응용인공지능 연구실. Deep Generative Model과 Probabilistic Graphical Model에 중점을 둡니다.

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising s…

Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

This paper proposes a time-efficient model for solving the Weapon-target assignment (WTA) problem with actorcritic reinforcement learning. While typical heuristic algorithms and recently studied artif…

Time-Efficient Weapon-Target Assignment by Actor-Critic Reinforcement

Agent-based models (ABMs) highlight the importance of simulation validation, such as qualitative face validation and quantitative empirical validation. In particular, we focused on quantitative valida…

Automatic Calibration Framework of Agent-Based Models for Dynamic and Heterogeneous Parameters

In recent years, developing a digital twin for a complex system has been a key research effort in the modeling and simulation (M&S) community. This paper presents one of the digital twin systems for a…

Modeling and Calibrating Digital Twin of Automatic Garbage Collection System in Sejong City

With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from dataset bias, mitigating …

Training Unbiased Diffusion Models From Biased Dataset

Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy…

Label-Noise Robust Diffusion Models

For learning with noisy labels, the transition matrix, which explicitly models the relation between noisy label distribution and clean label distribution, has been utilized to achieve the statistical …

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

The objective of domain generalization (DG) is to enhance the transferability of the model learned from a source domain to unobserved domains. To prevent overfitting to a specific domain, Sharpness-Aw…

Unknown Domain Inconsistency Minimization for Domain Generalization

In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require sig…

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

This paper presents FreD, a novel parameterization method for dataset distillation, which utilizes the frequency domain to distill a small-sized synthetic dataset from a large-sized original dataset. …

Frequency Domain-based Dataset Distillation

While deep neural networks play significant roles in many research areas, they are also prone to overfitting problems under limited data instances. To overcome overfitting, this paper introduces the f…

SAAL: Sharpness-Aware Active Learning

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Preference Optimization by Estimating the Ratio of the Data Distribution

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

Trajectory-Class-Aware Multi-Agent Reinforcement Learning

Distilling Dataset into Neural Field

Reward-based Input Construction for Cross-document Relation Extraction

Diffusion Rejection Sampling

LAGMA: LAtent Goal-guided Multi-agent Reinforcement Learning

Make Prompts Adaptable : Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior

Refine myself by teaching myself: Feature refinement via self-knowledge distillation

Adversarial dropout for supervised and semi-supervised learning

Mining social networks for personalized email prioritization

Analysis of twitter lists as a potential source for discovering latent characteristics of users

Dirichlet variational autoencoder

Refining generative process with discriminator guidance in score-based diffusion models

Modeling and simulating terrorist networks in social and geospatial dimensions

Soft truncation: A universal training technique of score-based diffusion model for high precision score estimation

Efficient extraction of domain specific sentiment lexicon with active learning

Counterfactual fairness with disentangled causal effect variational autoencoder

ORA User's Guide 2008

Augmented variational autoencoders for collaborative filtering with auxiliary information

Maximum likelihood training of implicit nonlinear diffusion model

Unknown-aware domain adversarial learning for open-set domain adaptation

Lada: Look-ahead data acquisition via augmentation for deep active learning

Diagnosis prediction via medical context attention networks using deep generative modeling

Sequential recommendation with relation-aware kernelized self-attention

Loss-curvature matching for dataset selection and condensation

Hierarchical context enabled recurrent neural network for recommendation

From noisy prediction to true label: Noisy prediction calibration via generative model

카이스트 응용인공지능 연구실

교수님 소개

문일철

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

문일철

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집