MMAI Lab · Ajou University

Multi-Modal Artificial Intelligence Lab

Multi-modal AI research connecting vision, language, and diverse signals for real-world impact.

Our research spans a broad range of machine learning problems, with particular emphasis on computer vision and robot learning. We are also interested in efficient deep learning, especially methods for compressing large language models. Our ultimate goal is to develop multimodal learning frameworks that integrate efficient large-scale vision models and LLMs for robotics, medical data and industrial applications. To this end, publishing our work at top-tier conferences is a key priority for our lab. We welcome inquiries from anyone interested in our research.

Computer VisionRobot LearningEfficient LLMsMedical AIIndustrial AI

MMAI Lab team gathered together for a group photo. — **Human Members**1 Professor, 9 PhD, 5 MS, 10 Interns

Researchers in a meeting room discussing vision AI projects. — **Non-Human Members**144 GPUs, 1 Robot

Latest News

Latest updates on our research, members, and achievements.

Sep 24, 2026

Paper Accepted

Publication

Two papers have been accepted at NeurIPS 2026

Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts · Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression

Sep 5, 2026

Paper Accepted

Publication

A paper has been accepted at CoRL 2026

FlowVLA: Enabling World Dynamics Understanding through Pluggable 3D Flow Learning

Sep 4, 2026

Paper Accepted

Publication

A paper has been accepted at Applied Energy

One-Cycle Based Battery Remaining Useful Life Prediction by Continuous Wavelet Scale Compression with Deep Neural Networks

Aug 21, 2026

Paper Accepted

Publication

A paper has been accepted at BMVC 2026

Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models

Computer Vision and Learning Algorithms

Visual Recognition

Large-scale Model

Meta Learning

Efficient Learning for LLMs

Model Compression

Efficient Learning

System-level Optimization

Robot Learning

VLA

Efficient Robotics

3D Recognition

Industrial and Medical AI

Battery AI

Fault Detection

Medical AI

Publications

Browse our latest publications and research highlights.

Figure 1 from Efficient Test-time Adaptation illustrating candidate verification and divergence-shift based test-time adaptation.

NeurIPS

Computer Vision and Learning Algorithms

Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts

Seungmin Oh, Seunghun Kang, Jongbin Ryu

Annual Conference on Neural Information Processing Systems (NeurIPS) · 2026-12-06

Figure 1 from Differentiable Bit-Widths showing SVD-based co-optimization of pruning and quantization for ultra-efficient LLM compression.

NeurIPS

Efficient Learning for LLMs

Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression

Hankyul Kang, Jongbin Ryu

Annual Conference on Neural Information Processing Systems (NeurIPS) · 2026-12-06

Figure 1 illustrating learnable text prompts and an augmented contrastive space built from image and text encoders over transformed image-text pairs, with adaptive re-calibration reweighting the contrastive loss targets.

BMVC

Computer Vision and Learning Algorithms

Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models

Seungmin Oh, Seunghun Kang, Jongbin Ryu

British Machine Vision Conference (BMVC) · 2026-11-23

Figure 1 showing FlowVLA: multimodal RGB, language, and proprioception inputs feed a VLA transformer backbone that decodes actions, with training-only dual-level supervision from reference-anchored 3D point trajectories at point and TCP flow levels.

CoRL

Robot Learning

Contact

We welcome inquiries from students, collaborators, and anyone interested in our lab. Please feel free to contact us using the contact information below. We work with many academic and industrial partners on practical learning algorithms and industrial AI applications

Address

Department of Artificial Intelligence, Ajou University

Padal Hall, Room 624,
Department of Artificial Intelligence, Ajou University,
206 World cup-ro, Yeongtong-gu,
Suwon 16499, Korea

General inquiries

jongbinryu@ajou.ac.kr

For collaboration, admissions, and project inquiries, please include your affiliation and topic.

More Information

Multi-Modal Artificial Intelligence Lab

Latest News

Research Areas

Computer Vision and Learning Algorithms

Efficient Learning for LLMs

Robot Learning

Industrial and Medical AI

Publications

Members

Jongbin Ryu

Research interests

Sungeun Kim

Research interests

Dooyeon Na

Research interests

HoHyeon Han

Research interests

Contact