Publications
Publications
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi, Sungroh Yoon, in Proceedings of International Conference on Machine Learning (ICML), Vancouver, Canada, July 2025.
paper link arXiv
Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
Mingi Jung, Saehyung Lee, Eunji Kim, Sungroh Yoon, in Proceedings of International Conference on Machine Learning (ICML), Vancouver, Canada, July 2025.
paper link arXiv
Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
Eunji Kim*, Siwon Kim*, Minjun Park, Rahim Entezari, Sungroh Yoon, in Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, June 2025. [* equal contribution]
paper link arXiv
DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
Jaewoo Song, Daemin Park, Kanghyun Baek, Sangyub Lee, Jooyoung Choi, Eunji Kim, Sungroh Yoon, in Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), Highlight Presentation, Nashville, USA, June 2025.
paper link arXiv
On Mitigating Stability-Plasticity Dilemma in CLIP-guided Image Morphing via Geodesic Distillation Loss
Yeongtak Oh, Saehyung Lee, Uiwon Hwang, Sungroh Yoon, International Journal of Computer Vision, vol. 133, pp. 2721-2751, https://doi.org/10.1007/s11263-024-02308-z, May 2025.
paper link arXiv
Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Sangwon Yu*, Jongyoon Song*, Bongkyu Hwang, Hoyoung Kang, Sooah Cho, Junhwa Choi, Seongho Joe, Taehee Lee, Youngjune Gwon, Sungroh Yoon, in Proceedings of Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), Oral Presentation, Albuquerque, USA, April 2025. [* equal contribution]
paper link arXiv
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
Sangwon Yu, Ik-hwan Kim, Jongyoon Song, Saehyung Lee, Junsung Park, Sungroh Yoon, in Findings of Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL Findings), Albuquerque, USA, April 2025.
paper link arXiv