Hyeonjeong Ha

Hyeonjeong Ha

📝 All Publications

« Back to home

Preprint

Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models Advancing Affordance-Grounded Creative Tool Use in Large Multimodal Models
[paper] [Project Page]
Cheng Qian*, Hyeonjeong Ha*, Jiayu Liu, Jeonghwan Kim, Emre Can Acikgoz, Bingxuan Li, Kunlun Zhu, Jiateng Liu, Aditi Tiwari, Zhenhailong Wang, Xiusi Chen, Heng Ji (* equal contribution)
UnderReview

2026

MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
[paper] [Project Page]
Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian, Jiayu Liu, William M. Campbell, Yue Wu, Yuji Zhang, Kathleen McKeown, Dilek Hakkani-Tur, Heng Ji
EMNLP 2026 (Findings)
Evaluating the Hidden Costs of Personalization in Large Language Models Evaluating the Hidden Costs of Personalization in Large Language Models
[paper]
Yumeng Wang, Yuchen Wu, Cheng Qian, Zhiyuan Fan, Hyeonjeong Ha, Shujin Wu, Jiayu Liu, Heng Ji, Ge Wang
EMNLP 2026 (Main)
CreativityBench: Evaluating Creative Reasoning via Affordance-Based Tool Repurposing CreativityBench: Evaluating Creative Reasoning via Affordance-Based Tool Repurposing
[paper] [Project Page]
Cheng Qian*, Hyeonjeong Ha*, Jiayu Liu, Bingxiang He, Jeonghwan Kim, Jiateng Liu, Bingxuan Li, Aditi Tiwari, Dwip Dalal, Zhenhailong Wang, Xiusi Chen, Mahdi Namazifar, Yunzhu Li, Heng Ji (* equal contribution)
COLM 2026
NarrativeTrack: Evaluating Video Language Models Beyond the Frame NarrativeTrack: Evaluating Video Language Models Beyond the Frame
[paper] [Apple Blog]
Hyeonjeong Ha, Jinjin Ge, Bo Feng, Kaixin Ma, Gargi Chakraborty
ECCV 2026 (Spotlight)
Securing Multimodal AI through Internal Information Decomposition Securing Multimodal AI through Internal Information Decomposition
[paper]
Jehyeok Yeon, Hyeonjeong Ha, Qiusi Zhan, Heng Ji
ICML 2026 (Spotlight)
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks 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)
ACL 2026 Main
ICLR 2026 Workshop on Principled Design for Trustworthy AI
Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning
[paper] [page]
Qiusi Zhan*, Hyeonjeong Ha*, Rui Yang, Sirui Xu, Hanyang Chen, Liangyan Gui, Yu-Xiong Wang, Huan Zhang, Heng Ji, Daniel Kang (* equal contribution)
ICLR 2026
PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning
[paper] [page]
Zhenhailong Wang, Xuehang Guo, Sofia Stoica, Haiyang Xu, Hongru Wang, Hyeonjeong Ha, Xiusi Chen, Yangyi Chen, Ming Yan, Fei Huang, Heng Ji
ICLR 2026
Energy-Based Transformers are Scalable Learners and Thinkers Energy-Based Transformers are Scalable Learners and Thinkers
[paper] [blog]
Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam, Peixuan Han, Hyeonjeong Ha, Aman Chadha, Yilun Du, Heng Ji, Jundong Li, Tariq Iqbal
ICLR 2026 (Oral)
Constructive Distortion: Multimodal LLMs with Test-Time Image Warping Constructive Distortion: Multimodal LLMs with Test-Time Image Warping
[paper]
Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra, Jeonghwan Kim, Madhav Kanda, Hyeonjeong Ha, Svetlana Lazebnik, Heng Ji, Unnat Jain
ICLR 2026
Must Read: A Systematic Survey of Computational Persuasion 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
ACM 2026, Computing Surveys

2025

PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding 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
NeurIPS 2025 (Spotlight)
SYNTHIA: Novel Concept Design with Affordance Composition SYNTHIA: Novel Concept Design with Affordance Composition
[paper] [page]
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)

2023

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
[paper]
Hyeonjeong Ha*, Minseon Kim*, Sung Ju Hwang (* equal contribution)
NeurIPS 2023
Effective Targeted Attacks for Adversarial Self-Supervised Learning Effective Targeted Attacks for Adversarial Self-Supervised Learning
[paper]
Minseon Kim, Hyeonjeong Ha, Sooel Son, Sung Ju Hwang
NeurIPS 2023

2022

Few-shot Transferable Robust Representation Learning via Bilevel Attacks Few-shot Transferable Robust Representation Learning via Bilevel Attacks
[paper]
Minseon Kim*, Hyeonjeong Ha*, Sung Ju Hwang (* equal contribution)
NeurIPS 2022 ML Safety Workshop