About Me

I’m currently a Research Scientist Intern at Meta Superintelligence Labs, where I work on agentic red-teaming for multi-service ecosystems. I received my Ph.D. in AI from KAIST, advised by Prof. Eunho Yang, and subsequently continued my research at the Machine Learning and Intelligence Lab as a Postdoctoral Researcher.

Research Interests

My research focuses on reliable multimodal and agentic AI, with an emphasis on (I) reliable multimodal AI, where I develop training-free methods for robust visual reasoning and study multimodal safety and fairness (with Viet Dac Lai, Adobe Research); (II) self-improving agents, which learn from failures through preference optimization and acquire new skills from experience (with Ninareh Mehrabi and Sina Shaham, Meta Superintelligence Labs); and (III) agentic red-teaming, which identifies safety risks across multi-service workflows and develops defenses for reliable deployment (with Ninareh Mehrabi, Meta Superintelligence Labs).

Preprints


  • Co-Evolving Agents: Learning from Failures as Hard Negatives [paper]
    Yeonsung Jung, Trilok Padhi, Sina Shaham, Dipika Khullar, Joonhyun Jeong, Ninareh Mehrabi†, Eunho Yang†

  • Web Agents Are Still Greedy: Progress-Aware Action Generation and Selection via Meta-Plan
    Joonhyun Jeong, Gilhyun Nam, Yeonsung Jung, Eunho Yang

  • 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

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

Conference Publications


  • Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing [paper]
    Joowon Kim, Ziseok Lee, Donghyeon Cho, Sanghyun Jo, Yeonsung Jung, Kyungsu Kim, Eunho Yang
    ICCV 2025

  • Preserve or Modify? Context-Aware Evaluation 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
    CVPR 2025

  • Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy [paper]
    Joonhyun Jeong, Seyun Bae, Yeonsung Jung, Jaeryong Hwang, Eunho Yang
    CVPR 2025

  • 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 2020

  • 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 2018

Work Experiences


  • Research Scientist Intern, Meta Superintelligence Labs, Menlo Park, CA. (May 2026 - Nov. 2026)
    • Agentic red-teaming for multi-service ecosystems.
  • External Collaborator, NAVER AI, Seongnam, South Korea. (Sept. 2023 - Feb. 2024)
    • Robust learning for neural radiance fields; PruNeRF (ICML 2024).
  • Research Intern, NAVER Search, Seongnam, South Korea. (July 2019 - Aug. 2019)
    • Graph-based ranking and search relevance for production systems.

Academic Services


  • Workshop Organizer
  • 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)
    • International Conference on Computer Vision (ICCV)
    • Association for the Advancement of Artificial Intelligence (AAAI)
    • Artificial Intelligence and Statistics (AISTATS)
    • NAACL Workshop on TrustNLP

Lectures


  • SAMSUNG DS   SAMSUNG DS (2020–2022)
  • LG Electronics   LG Electronics (2022)
  • HD Hyundai   HD Hyundai (2023)
  • LG Innotek   LG Innotek (2022–2024)
  • LG Chem   LG Chem (2022)
  • DSME   DSME (2022–2023)

Recent posts