Multisensory Intelligence Lab

We are a research group at UNIST (Ulsan National Institute of Science and Technology), led by Prof. Arda Senocak. Our work spans the intersection of perception, representation, and learning across multiple sensory modalities.

We develop machine learning models that perceive and reason about the world through multiple senses — as humans do. Our research encompasses multimodal learning with the goal of building AI systems that are grounded in rich, diverse streams of real-world signals.

Multimodal Learning Audio-Visual Learning Visuo-Tactile Learning Visuo-Olfactory Learning Audio/Speech Processing

People

See all →
Arda

Arda Senocak

Principal Investigator

Yewon Kim

Yewon Kim

PhD Student

Jeonghwan Lee

Jeonghwan Lee

MS-Ph.D Integrated
(co-advised with Prof. Kyungdon Joo)

Sanghyeok

Sanghyeok Lee

Researcher

Jimmy

Chuong (Jimmy) Tran

Undergraduate Intern

join us

Is That You?

Join Us!

Join MILab

We are actively looking for motivated PhD/MS students and Undergraduate interns passionate about multimodal learning and sensory AI. If you are interested, please click the button below to see how to apply.

Join Our Lab

Selected News

See all →
Oct 2026
Award

MILab has been selected for OpenAI’s Academic Researcher program, receiving one year of free access to the ChatGPT Pro 200 tier.

Oct 2026
Paper

One paper is accepted to IJCV 2026.

June 2026
Paper

One paper is accepted to ECCV 2026 as Oral paper ⭐.

March 2026
Award

MILab has been awarded a 3-year research grant from the National Research Foundation of Korea (NRF) under the Outstanding Young Scientist Grant (우수신진연구).

Feb 2026
Paper

Three main conference papers (1 Highlight ⭐) are accepted to CVPR 2026.

Publications

See all →

* Equal Contribution   ·   † Corresponding Author

Sound2Vision teaser

Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment

Sung Bin Kim, Arda Senocak, Hyunwoo Ha, Tae-Hyun Oh

IJCV 2026

See_Sniff teaser

See & Sniff: Learning Visuo-Olfactory Representations

Seongyu Kim*, Seungwoo Lee*, Hyeonggon Ryu, Joon Son Chung, Arda Senocak†

ECCV 2026 Selected as Oral Paper ⭐(† Corresponding Author)

Seeing Through Touch teaser

Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions

Seongyu Kim, Seungwoo Lee, Hyeonggon Ryu, Joon Son Chung, Arda Senocak†

CVPR 2026 († Corresponding Author)

Synthetic SSL teaser

How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?

Arda Senocak*, Sooyoung Park*, Tae-Hyun Oh, Joon Son Chung

CVPR 2026 Selected as Highlight Paper ⭐ (* Equal Contribution)

CASS teaser

Cinematic Audio Source Separation Using Visual Cues

Kang Zhang*, Suyeon Lee*, Arda Senocak†, Joon Son Chung†

CVPR 2026 († Co-Corresponding Author)