Publications

2026

  1. spatial_transfusion.png
    Spatial Transfusion: From Structured Spatial Scene Understanding to Generation and Editing
    Jaeyeon Kim , Sebastian Braun, and Hannes Gamper
    arXiv preprint, 2026
    Paper Project Page
  2. llt.png
    Long Listening Thoughts: Eliciting Open Auditory Reasoning with Deliberative Perception and Cognitive Refinement
    Jaeyeon Kim , Chao-Han Huck Yang, Luoyi Zhang, Chan-Jan Hsu, Fernando Ruiloba Portilla , and 3 more authors
    In Findings of EMNLP, 2026
    Paper Project Page
  3. listen_to_latents.png
    Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions
    Chan-Jan Hsu,  Jaeyeon Kim , Chao-Han Huck Yang, Shinji Watanabe, Hung-yi Lee , and 1 more author
    In Findings of EMNLP, 2026
    Paper
  4. k_browsecomp.png
    K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
    Nahyun Lee, Dongkeun Yoon, Guijin Son, Geewook Kim, Dayoon Ko , and 10 more authors
    In Findings of EMNLP, 2026
    Paper GitHub
  5. comparative_reasoning.png
    Comparative Reasoning: Making an Audio Language Model Better at Comparing Emotions
    Abinay Reddy Naini*,  Jaeyeon Kim* , Chao-Han Huck Yang, Shinji Watanabe, and Carlos Busso
    In Interspeech (Oral), 2026
    Paper Project Page
  6. audio_reasoning_challenge.png
    The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agents
    Ziyang Ma, Ruiyang Xu, Yinghao Ma, Chao-Han Huck Yang, Bohan Li , and 7 more authors
    In Interspeech, 2026
    Paper Project Page
  7. wow_bench.png
    WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations
    Jaeyeon Kim , Heeseung Yun, Tony Woo, Chao-Han Huck Yang, and Gunhee Kim
    In Findings of ACL, 2026
    Paper Project Page
  8. scene_aware_v2sa.png
    Towards Scene-Aware Video-to-Spatial Audio Generation
    Jaeyeon Kim* , Heeseung Yun*, and Gunhee Kim
    International Journal of Computer Vision (IJCV), 2026
    Paper
  9. dcase_aqa.png
    Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning
    Chao-Han Huck Yang, Sreyan Ghosh, Qing Wang,  Jaeyeon Kim , Hengyi Hong , and 12 more authors
    In ICASSP, 2026
    Paper

2025

  1. eba.png
    Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span
    Heeseung Yun, Joonil Na,  Jaeyeon Kim , Calvin Murdock, and Gunhee Kim
    In NeurIPS (Spotlight), 2025
    Paper
  2. visage.png
    ViSAGe: Video-to-Spatial Audio Generation
    Jaeyeon Kim , Heeseung Yun, and Gunhee Kim
    In ICLR, 2025
    Paper Project Page

2024

  1. enclap++.png
    EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance
    Jaeyeon Kim , Minjeong Jeon, Jaeyoon Jung, Sang Hoon Woo, and Jinjoo Lee
    In DCASE2024 Workshop, 2024
    Paper
  2. Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning
    Jaeyeon Kim , Jaeyoon Jung, Sang Hoon Woo, Minjeong Jeon, and Jinjoo Lee
    DCASE2024 Challenge Technical Report, 2024
    2nd Place Paper
  3. learning_semantic.png
    Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations
    Jaeyeon Kim , Injune Hwang, and Kyogu Lee
    In ICASSP (Oral), 2024
    Paper
  4. enclap.png
    EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning
    Jaeyeon Kim , Jaeyoon Jung, Jinjoo Lee, and Sang Hoon Woo
    In ICASSP, 2024
    Paper GitHub

2023

  1. pits.png
    PITS: Variational pitch inference without fundamental frequency for end-to-end pitch-controllable TTS
    Junhyeok Lee, Wonbin Jung, Hyunjae Cho,  Jaeyeon Kim , and Jaehwan Kim
    In ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023
    Paper GitHub