I am a PhD student at Blender Lab at University of Illinois, Urbana-Champaign (UIUC), currently advised by Prof. Heng Ji. I obtained my Master’s from the Graduate School of AI at KAIST, under the supervision of Prof. Sung Ju Hwang. If you are interested in collaborating with me on research projects, please contact me! Here is my CV.

My primary research interest includes:

• Visual Perception Capability of Multimodal Large Language Models (MLLMs)
• Trustworthiness of MLLM-powered Framework (e.g., Embodied Agents, RAG)
• Model Interpretability & Robustness

🔥 News

• 2025.05:  🎉🎉 One paper accepted to ACL 2025
• 2025.01:  🎉🎉 Excited to start Machine Learning Research Internship at Apple from Summer 2025!
• 2024.08:  🤘🤘 Excited to start my Ph.D. program at UIUC!
• 2023.09:  🎉🎉 Two paper accepted to NeurIPS 2023 Conference
• 2023.06:  🎉🎉 One paper accepted to ICML 2023 AdvML-Frontiers’ Workshop
• 2022.08:  🎉🎉 Two papers accepted to NeurIPS 2022 ML Safety Workshop

📝 Publications

• SYNTHIA: Novel Concept Design with Affordance Composition

  [paper]
  Hyeonjeong Ha *, Xiaomeng Jin *, Jeonghwan Kim, Jiateng Liu, Zhenhailong Wang, Khanh Duy Nguyen, Ansel Blume, Nanyun Peng, Kai-wei Chang, Heng Ji (*: equal contribution)
  ACL 2025 (Main)

• MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks

  [paper]
  Hyeonjeong Ha *, Qiusi Zhan *, Jeonghwan Kim, Dimitrios Bralios, Saikrishna Sanniboina, Nanyun Peng, Kai-wei Chang, Heng Ji (*: equal contribution)
  preprint

• BEATing Safety: Backdoor Attacks on Vision-Driven Embodied Agents via Contrastive Trigger Learning

  Qiusi Zhan *, Hyeonjeong Ha *, Rui Yang, Sirui Xu, Hanyang Chen, Liangyan Gui, Yu-Xiong Wang, Huan Zhang, Heng Ji, Daniel Kang (*: equal contribution)
  Under Review

• PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding

  [paper]
  Ansel Blume, Jeonghwan Kim, Hyeonjeong Ha, Elen Chatikyan, Xiaomeng Jin, Khanh Duy Nguyen, Nanyun Peng, Kai-Wei Chang, Derek Hoiem, Heng Ji
  Under Review

• Energy-Based Transformers are Scalable Learners and Thinkers

  Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam, Peixuan Han, Hyeonjeong Ha, Aman Chadha, Yilun Du, Heng Ji, Jundong Li, Tariq Iqbal
  Under Review

• Constructive Distortion: Multimodal LLMs with Test-Time Image Warping

  Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra, Jeonghwan Kim, Madhav Kanda, Hyeonjeong Ha, Svetlana Lazebnik, Heng Ji, Unnat Jain
  Under Review

• Must Read: A Systematic Survey of Computational Persuasion

  [paper]
  Nimet Beyza Bozdag, Shuhaib Mehri, Xiaocheng Yang, Hyeonjeong Ha, Zirui Cheng, Esin Durmus, Jiaxuan You, Heng Ji, Gokhan Tur, Dilek Hakkani-Tür
  preprint

• Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

  [paper]
  Hyeonjeong Ha *, Minseon Kim *, Sung Ju Hwang (*: equal contribution)
  NeurIPS 2023
  ICML 2023 The 2ND New Frontiers in Adversarial Machine Learning Workshop

• Effective Targeted Attacks for Adversarial Self-Supervised Learning

  [paper]
  Minseon Kim, Hyeonjeong Ha, Sooel Son, Sung Ju Hwang
  NeurIPS 2023

• Few-shot Transferable Robust Representation Learning via Bilevel Attacks

  [paper]
  Minseon Kim *, Hyeonjeong Ha *, Sung Ju Hwang (*: equal contribution)
  NeurIPS 2022 ML Safety Workshop

📖 Educations

• 2024.08 - Present, Ph.D in Computer Science, UIUC.
• 2022.02 - 2024.02, M.S. in Graduate School of AI, KAIST.
• 2017.02 - 2022.02, B.S. in Computer Science (major) and Bio & Brain Engineering (minor), KAIST.

💻 Work Experience

• 2025.05 - 2025.08, Machine Learning Research Intern at Apple, Data & Machine Learning Innovation team, Seattle, WA, USA.
• 2024.02 - 2024.07, Full-time Employee at Samsung Research, Language Intelligence Team, Seoul, South Korea.
• 2020.09 - 2021.02, Developer Intern at NAVER, Seongnam, South Korea.
• 2020.06 - 2020.08, Undergraduate Research Intern at KIXLAB, KAIST, Daejeon, South Korea. Prof: Juho Kim
• 2019.06 - 2019.12, Developer Intern at H2K, Daejeon, South Korea.

👩‍💻 Academic Service

• Reviewer: ICML (2024, 2023), NeurIPS (2023)