Young Jin Ahn

Youngjae Joo

Seongmin Lee

JooBon Maeng

Haanvid Lee

HyeongJoo Hwang

Ohjoon Kwon

Tri Wahyu Guntara

Jinjae Lee

Seonghyun Ban

Jaewook Shin

Seunghyun Hwang

Jaeseok Yoon

Haeju Lee

Sungyoon Kim

Youngsoo Jang

Geon-Hyeong Kim

Jongmin Lee

Sunghoon Hong

Deunsol Yoon

Jinhyeon Kim

Youngjune Lee

Donghoon Ham

Jeong-Gwan Lee

Byung-Jun Lee

Shinhyung Kim

Wonseok Jeon

Kanghoon Lee

Soohyun Lim

Jiyeon Ham

Daehyun Lee

Taekgyu Hong

Jungpyo Hong

Hyeoneun Kim

Daejoong Kim

Jaedeug Choi

Bongseok Goh

Beom-Yong Ha

Heejin Lim

Dongho Kim

Eunsoo Oh

Youngwook Kim

Dajinseol Jeon

Artificial Intelligence & Probabilistic Reasoning Lab. Models and algorithms for decision theoretic problems, including large scale Markov decision processes (MDPs) and partially observable MDPs (POMDPs)
Model representations
Model learning
Efficient algorithms and their applications

인공지능 & 확률적 추론 연구실. 대규모 Markov 의사 결정 프로세스 (MDP) 및 부분적으로 관찰 가능한 MDP (POMDP)를 포함한 의사 결정 이론 문제에 대한 모델 및 알고리즘 모델 표현 모델 학습 효율적인 알고리즘 및 응용

DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization

Dynamic VLM-Guided Negative Prompting for Diffusion Models

조건부 변분 오토인코더를 활용한 대규모 언어 모델의 추론 성능 향상 기법

순위 가중 보상을 활용한 대규모 언어 모델의 강화학습 기반 최적화

Goal-Conditioned DPO: Prioritizing Safety in Misaligned Instructions

Monet: Mixture of Monosemantic Experts for Transformers

Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning

Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction

Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models

GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets

SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL

Diversification of Adaptive Policy for Effective Offline Reinforcement Learning

디퓨전 모델의 소량 데이터 학습자로서 활용한 다양한 데모 데이터로부터의 오프라인 모사 학습

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies

Learning to cooperate via policy search

Solving very large weakly coupled Markov decision processes

Learning finite-state controllers for partially observable environments

Solving POMDPs by searching the space of finite policies

End-to-end neural pipeline for goal-oriented dialogue systems using GPT-2

Inverse reinforcement learning in partially observable environments

Nonparametric Bayesian inverse reinforcement learning for multiple reward functions

An improved particle filter with a novel hybrid proposal distribution for quantitative analysis of gold immunochromatographic strips

OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation

Map inference for bayesian inverse reinforcement learning

Demodice: Offline imitation learning with supplementary imperfect demonstrations

Hand grip pattern recognition for mobile user interfaces

Monte-Carlo tree search for constrained POMDPs

Closing the gap: Improved bounds on optimal POMDP solutions

Approximate linear programming for constrained partially observable Markov decision processes

Coptidice: Offline constrained reinforcement learning via stationary distribution correction estimation

Point-based value iteration for constrained POMDPs

Method and apparatus for inputting function of mobile terminal using user's grip posture while holding mobile terminal

Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-Critic

KAIST AIPR Lab

교수님 소개

김기응

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization

Dynamic VLM-Guided Negative Prompting for Diffusion Models

조건부 변분 오토인코더를 활용한 대규모 언어 모델의 추론 성능 향상 기법

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

김기응

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization

Dynamic VLM-Guided Negative Prompting for Diffusion Models

조건부 변분 오토인코더를 활용한 대규모 언어 모델의 추론 성능 향상 기법

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집