Jin-Jun Lee
Korea Advanced Institute of Science and Technology · Neuroscience
About the Lab
Professor Jin-Jun Lee's research lab at KAIST specializes in the intersection of media art, artificial intelligence, and embodied interaction, focusing on creating immersive, multisensory experiences through innovative technologies. The lab explores AI-driven artistic expression, including data mosaicing, sonification, and interactive projection systems, to address social and cultural narratives—particularly the voices of marginalized communities. Their work bridges traditional East Asian literati aesthetics with contemporary digital media, using computational systems to translate inner emotional and mental states into multimodal artistic outputs. The lab emphasizes ethical and aesthetic implications of AI in art, challenging dominant representations through palimpsestic, layered computational artworks.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
5As interactive media arts evolve, there is a growing demand for technologies that offer multisensory experiences beyond audiovisual elements in large-scale projection mapping exhibitions. However, traditional methods of providing tactile feedback are impractical in expansive settings due to their bulk and complexity. The EMPop system is the proposed solution, utilizing a straightforward design of electromagnets and permanent magnets making projection mapping more interactive and engaging. Our sy
Abstract The authors present gOd, mOther and sOldier—Nowhere in Somewhere Series 2022, a work that was conceptualized and created by artist Jinjoon Lee and his TX Creative Media Lab at KAIST, realized through the remote cooperation of eight local collaborators across Southeast Asia. The authors used artificial intelligence–based object detectors and sonification techniques in a work of media art to symbolize the voicelessness of those at the margins of society in Southeast Asia. These algorithms
We introduce an efficient algorithm for general data mosaicing, based on the simulation-based inference paradigm. Our algorithm takes as input a target datum, source data, and partitions of the target and source data into fragments, learning distributions over averages of fragments of the source data such that samples from those distributions approximate fragments of the target datum. We utilize a model that can be trivially parallelized in conjunction with the latest advances in efficient simul
This paper examines diffused multiplicity as an emergent characteristic of AI art, analyzing how multiple temporal, cultural, and aesthetic layers are embedded within these computational systems. Unlike traditional artistic production that maintains coherent aesthetic identities, AI artworks function as palimpsestic objects that contain multiple potential interpretations simultaneously. Through analysis of neural networks as synthetic media and examination of related artworks, this paper demonst
Abstract This paper analyzes the integration of East Asian literati traditions with contemporary multimedia through two artworks. It proposes a multimodal transcoding framework converting video frames into multisensory outputs via data-driven visualization and sonification. Using a modified turntable, the system interprets an artificial marble disc, created from the artist’s daily creation, to depict mental space using sumi ink. This aligns with literati traditions of expressing inner worlds thr
Research Areas
Dive deeper into Jin-Jun Lee's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.