About Me

I’m a Ph.D candidate at Machine Learning and Intelligence Lab (MLILAB) at KAIST in South Korea, advised by Prof. Eunho Yang.

My recent research interests focus on (i) self-improving large multi-modal agents for generalization (closely working with Ninareh Mehrabi and Sina Shaham ) and (ii) addressing hallucination in multi-modal large language models . I am also interested in developing (iii) robust fine-tuning methods for vision-language models to ensure reliable deployment in real-world applications. Previously, my work centered on understanding and improving model robustness across diverse modalities, including 2D and 3D vision, graph, and multi-modal models.

Please feel free to contact me if you are interested in potential collaborations!   LinkedIn

Conference Publications

• LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding [paper]
  Doohyuk Jang*, Sihwan Park*, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu, Sung-Yub Kim†, Eunho Yang†
  ICLR 2025

• A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective [paper]
  Yeonsung Jung*, Jaeyun Song*, June Yong Yang, Jin-Hwa Kim, Sung-Yub Kim, Eunho Yang
  NeurIPS 2024

• PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency [paper]
  Yeonsung Jung, Heecheol Yun, Joonhyung Park, Jin-Hwa Kim†, Eunho Yang†
  ICML 2024

• Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation [paper]
  Yeonsung Jung, Hajin Shim, June Yong Yang, Eunho Yang
  ICML 2023

• Scalable Anti-TrustRank with Qualified Site-level Seeds for Link-based Web Spam Detection [paper]
  Joyce Jiyoung Whang, Yeonsung Jung, Seonggoo Kang, Dongho Yoo, Inderjit S. Dhillon
  The Web Conf. Workshop on CyberSafety: Computational Methods in Online Misbehavior 2024

• Fast Asynchronous Anti-TrustRank for Web Spam Detection [paper]
  Joyce Jiyoung Whang, Yeonsung Jung, Inderjit S. Dhillon, Seonggoo Kang, Jungmin Lee
  WSDM Workshop on MIS2: Misinformation and Misbehavior Mining on the Web 2024

Preprints

• Augmentation-Driven Metric for Balancing Preservation and Modification in Text-Guided Image Editing [paper]
  Yoonjeon Kim*, Soohyun Ryu*, Yeonsung Jung, Hyunkoo Lee, Joowon Kim, June Yong Yang, Jaeryong Hwang, Eunho Yang
  under review

• Playing the Fool: Jailbreaking Large Language Models with Out-of-Distribution Strategies
  Joonhyun Jeong, Seyun Bae, Yeonsung Jung, Jaeryong Hwang, Eunho Yang
  under review

• MeZO-A³dam: Memory-efficient Zeroth-order Adam with Adaptivity Adjustments for Fine-tuning LLMs
  Sihwan Park*, Jihun Yun*, Sung-Yub Kim, June Yong Yang, Yeonsung Jung, Souvik Kundu, Kyungsu Kim, Eunho Yang
  under review

• 3D Scene Decomposition Under Occlusion via Multi-View-Aware Inpainting
  Heecheol Yun, Yeonsung Jung, Eunho Yang
  under review

Work Experiences

• Research Intern, NAVER, Seongnam, South Korea. (July 2019 - Sept. 2019)
  • Improve searching performance through click graph neural networks.

Acamdeic Services

• Conference Reviewer
  • Neural Information Processing Systems (NeurIPS)
  • International Conference on Machine Learning (ICML)
  • International Conference on Learning Representations (ICLR)
  • Computer Vision and Pattern Recognition (CVPR)
  • Artificial Intelligence and Statistics (AISTATS)

Recent posts