Junyoung Koh

Ph.D Student at Yonsei University, South Korea. Currently working at KRAFTON (PUBG). Research interest in Music Information Retrieval and Generative AI.

[arXiv Sound @ArxivSound]

Joonyong Park, Jungwoo Kim, Junyoung Koh, Yuki Saito, "Probing Token Spaces under Generator Shift in AI-Generated Music Detection," https://t.co/3rpWOdcC2o

[Sound Papers @SoundPapers]

Instrumental Text-to-Music Generation with Auxiliary Conditioning Branches

Junyoung Koh
https://t.co/rjuHVPbJAI [𝚌𝚜.𝚂𝙳]

[Natural Language Processing Papers @HEI]

MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following

Jaeyun Lee, Junyoung Koh, Zeynel Tok, Hunar Batra, Ronald Clark
https://t.co/X0Ro0KengV [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]
💬GEM Workshop at ACL 2026

[Junyoung Koh @JUNFROMAI]

@nukemusso @aclmeeting Thank you!!!

[Junyoung Koh @JUNFROMAI]

I'm happy to share that our paper, 'Jamendo-MT-QA : A Benchmark for Multi-Track Comparative Music Question Answering' has been accepted at #ACL2026 Findings! @aclmeeting

A huge thanks to all my co-authors and proud to be lead of #MAAP Music AI Community LAB!

[arXiv Sound @ArxivSound]

Junyoung Koh, Jaeyun Lee, Soo Yong Kim, Gyu Hyeong Choi, Jung In Koh, Jordan Phillips, Yeonjin Lee, Min Song, "Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering," https://t.co/OOy8Uck4Ao

[Information Retrieval Papers @CsIR_papers]

Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering

Junyoung Koh, Jaeyun Lee, Soo Yong Kim, Gyu Hyeong Choi, Jung In Koh, Jordan Phillips, Yeonjin Lee, Min Song
https://t.co/mKW3CZma8J [𝚌𝚜.𝙸𝚁 𝚌𝚜.𝙼𝙼 𝚌𝚜.𝚂𝙳]

[Junyoung Koh @JUNFROMAI]

✨ Excited to share that our paper, “Let Triggers Control: Frequency-Aware Dropout for Effective Token Control”, has been accepted to the P13N: Personalization in Generative AI Workshop at @CVPR #CVPR2026! #GenerativeAI #Personalization #ComputerVision #P13N

[arXiv Sound @ArxivSound]

Junyoung Koh, Soo Yong Kim, Yongwon Choi, Gyu Hyeong Choi, "Jamendo-QA: A Large-Scale Music Question Answering Dataset," https://t.co/49O9UYAXD3

[arXiv Sound @ArxivSound]

Junyoung Koh, Soo Yong Kim, Gyu Hyeong Choi, Yongwon Choi, "AIBA: Attention-based Instrument Band Alignment for Text-to-Audio Diffusion," https://t.co/nLfdjmGmLw

[Junyoung Koh @JUNFROMAI]

✨ I am pleased to share that our paper, “AIBA: Attention-based Instrument Band Alignment for Text-to-Audio Diffusion”, has been accepted to the @WorkshopAi48148 AI for Music Workshop #NeurIPS 2025!

The name AIBA was inspired by Masaki Aiba from my favorite group #ARASHI (#嵐).