카이스트 응용인공지능 연구실

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

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

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

Training Unbiased Diffusion Models From Biased Dataset

Label-Noise Robust Diffusion Models

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

Unknown Domain Inconsistency Minimization for Domain Generalization

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

Frequency Domain-based Dataset Distillation

SAAL: Sharpness-Aware Active Learning

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…
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…
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…
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 …
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…
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 …
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…
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…
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. …
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…
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…

Announcements

Selected Publications