Vision AI Lab

Recruiting grad students

KAIST · School of Computing

Information sourcenot verified yet

This lab is recruiting graduate students

InnoCore 박사후연구원, 대학원생, 학부 인턴 모집

Apply / Contact

Ask current students about this lab

Post your question to the Career board — students who have verified their school can answer under blind identities.

Professor

Prof. 김현우

Professor's page · publications

About

KAIST 전산학부 김현우(Hyunwoo J. Kim) 교수의 Machine Learning & Vision Lab(MLV)으로, 2025년 2월 고려대에서 KAIST로 옮겨 신설되었다. 머신러닝과 컴퓨터 비전의 근본 문제를 다루며 비디오 파운데이션 모델·비디오 질의응답·비디오-언어 모델 등 고차원 시각 인지와 멀티모달 과학 데이터 이해·생성에 집중한다. AGI를 지향하는 연구를 표방한다.

Research keywords

AIcomputer visionmachine learning

Selected publications

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCVPR · 2025
LLaMo: Large Language Model-based Molecular Graph AssistantNeurIPS · 2024
DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPONeurIPS · 2025
Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality GenerationNeurIPS · 2025
Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video RetrievalICCV · 2025
Representation Shift: Unifying Token Compression with FlashAttentionICCV · 2025

Other labs in this department

See all labs in this department