Multimodal Language Processing Lab.
KAIST 멀티모달 자연어처리 연구실 (임경태 교수와 MLP랩)
https://sites.google.com/view/aailab
Embedded Files
News
News
(2026, Sep.) Hoyun Song (송호윤) joined DanKook University as a faculty member.
(2026, Aug.) Seven papers are accepted to EMNLP2026
(2026, July.) Hyeonseok Lim (임현석) joined ETRI as a Researcher.
(2026, July.) ChangSu Choi (최창수) joined DeNA, Japan as an AI Specialist.
(2026, July.) SeoHyun Song (송서현) joined SoulArt after graduation
(2026, May.) Our paper is accepted to International Journal of Human–Computer Interaction (SCIE)
(2026, April.) Four papers are accepted to ACL2026
(2025, April) Our laboratory has been selected for the "디지털 딥페이크 대응 핵심기술개발" research project (IITP)
(2025, Mar) Our laboratory has been selected for the "핵심연구(C유형, 1.5 billion KRW)" research project (NRF)
(2026, Mar.) Our paper is accepted to Scientific Reports (SCIE)
(2026, Jan.) Our paper is accepted to LRE (SCIE)
(2026, Jan.) Four papers are accepted to EACL2026
(2025, Aug.) Dongjae Shin (신동재) joined Tutorus Labs after graduation.
(2025, Aug.) Our laboratory has been selected for the "우수신진" research project (NRF)
(2025, Aug.) Two papers are accepted to EMNLP2025
Research
KAIST 멀티모달 언어처리 연구실(MLP Lab)은 (1) 한국어 언어자원 설계 (2) 전통 자연어처리 (3) 멀티모달 초거대 언어모델을 연구합니다
Large Language Model (LLM) & dataset
Large Language Model (LLM) & dataset
KORMo and Bllossom: Building and Scaling the First Korean–English 10B-Scale Foundation Models from Scratch in an Academic Lab
Research and dissemination of fully open-source Korean LLMs
Efficient bilingual tokenizer design and analysis
Observing pre-training performance across diverse data composition strategies
Domain-specialized vision–language models
Knowledge transfer using agent-style teacher models
Large Language Model (LLM) & dataset based on Linguistic features
Large Language Model (LLM) & dataset based on Linguistic features
Lead of the Bllossom project. (https://www.bllossom.ai) (https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
Lead of the Universal Korean Language Resource project. (https://sites.google.com/view/universal-korean)
Visual language model & Video Story Understanding
Visual language model & Video Story Understanding
Visual Question Answering (VQA) is a question answering system that answers user's questions based on the input image and question.
Bllossom-V: Vision-Language Model
Bllossom-V: Vision-Language Model
What we have done (KBVQA Chatbot)
What we have done (KBVQA Chatbot)
Applied Artificial Intelligence on Robotics
Applied Artificial Intelligence on Robotics
Vision-Language-Action Model
Control of Robots Based on Speech Teaching Command
Nvidia Jetson Nano, Jet Racer, Jet racer pro
Spot (Boston Dynamics)
Page updated
Google Sites
Report abuse