기계 인지 및 추론 연구실
Machine Perception and Reasoning Lab.
지도 최종현 교수
연구 컴퓨터 비전, 머신러닝, 멀티모달 인공지능, 자연어 처리
TEL 02-880-1766
WEBSITE https://mpr.snu.ac.kr
소개자료 snumpr_poster.pdf
연구실 소개 및 연구분야
저희 연구실은 시각 인식과 기계 추론을 연구하는 연구실입니다. 컴퓨터 비전, 머신러닝, 자연어처리, 로보틱스 등 다양한 분야에 걸쳐 논문을 읽고, 코딩하고, 토론하고 논문을 작성합니다. 열정있는 대학원생과 학부 인턴을 모집하고 있습니다. 연구실 홈페이지 "Join Us" 페이지에서 자세한 내용을 보실 수 있습니다.
최근 관심분야 및 주요 연구과제
컴퓨터 비전
머신러닝
멀티모달 AI
Embodied AI
Continual Learning
Binary Network
Neuromorphic (event) camera
자연어 처리
머신러닝
멀티모달 AI
Embodied AI
Continual Learning
Binary Network
Neuromorphic (event) camera
자연어 처리
주요 논문/특허
- Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts, Taewook Kang*, Taeheon Kim*, Donghyun Shin, Jonghyun Choi, ECCV 2026
- SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models, Hyeonbeom Choi, Daechul Ahn, Youhan Lee, Taewook Kang, Seongwon Cho, Jonghyun Choi, ICML 2026 (Spotlight, Top 2.2%)
- Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling, Minhyuk Seo, Hyunseo Koh, Jonghyun Choi, ICLR 2025 - Spotlight
- Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback, Daechul Ahn, Yura Choi, Youngjae Yu, Dongyeop Kang, Jonghyun Choi, ACL 2024 - Oral
- Pre-emptive Action Revision by Environmental Feedback for Embodied Instruction Following Agents, Jinyeon Kim*, Cheolhong Min*, Byeonghwi Kim, Jonghyun Choi, CoRL 2024
- Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents, Byeonghwi Kim, Jinyeon Kim, Yuyeong Kim, Cheolhong Min, Jonghyun Choi, ICCV 2023
- Ask4Help: Learning to Leverage an Expert for Embodied Tasks, Kunal Pratap Singh, Luca Weihs, Alvaro Herrasti, Jonghyun Choi, Aniruddha Kembhavi, Roozbeh Mottaghi, NeurIPS 2022
- SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models, Hyeonbeom Choi, Daechul Ahn, Youhan Lee, Taewook Kang, Seongwon Cho, Jonghyun Choi, ICML 2026 (Spotlight, Top 2.2%)
- Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling, Minhyuk Seo, Hyunseo Koh, Jonghyun Choi, ICLR 2025 - Spotlight
- Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback, Daechul Ahn, Yura Choi, Youngjae Yu, Dongyeop Kang, Jonghyun Choi, ACL 2024 - Oral
- Pre-emptive Action Revision by Environmental Feedback for Embodied Instruction Following Agents, Jinyeon Kim*, Cheolhong Min*, Byeonghwi Kim, Jonghyun Choi, CoRL 2024
- Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents, Byeonghwi Kim, Jinyeon Kim, Yuyeong Kim, Cheolhong Min, Jonghyun Choi, ICCV 2023
- Ask4Help: Learning to Leverage an Expert for Embodied Tasks, Kunal Pratap Singh, Luca Weihs, Alvaro Herrasti, Jonghyun Choi, Aniruddha Kembhavi, Roozbeh Mottaghi, NeurIPS 2022
