Hyunji Amy Lee
Postdoc at UNC NLP
hyunjil at cs.unc.edu
About
Hello! I am a postdoctoral research associate at UNC working with Mohit Bansal. I completed my Ph.D. from KAIST AI, where I was advised by Minjoon Seo. My research focuses on developing and evaluating models and agentic systems that can adapt to dynamic, multimodal knowledge over long horizons. I am broadly interested in continual updates to parametric knowledge, coordination between parametric knowledge and evolving external knowledge through adaptive retrieval and memory, and understanding adaptation in real-world settings with evolving multimodal information and long-range dependencies.My research has been recognized through selection as an ML and Systems Rising Star, Best Paper and Best Student Paper at KnowFM'25 and Knowledge-Augmented NLP'24, and as a Qualcomm Innovation Fellowship Finalist'23.
I've previously interned at Microsoft Research (Summer 2025) with Lucas Caccia, Marc-Alexandre Côté, Eric Xingdi Yuan, and Alessandro Sordoni;Tencent AI (Winter 2024) with Wenhao Yu, Kaixin Ma, and Hongming Zhang; Adobe Research (Summer 2024) with David Seunghyun Yoon, Franck Dernoncourt, and Trung Bui; AI2 Semantic Scholar Team (Summer 2023) with Kyle Lo, Luca Soldaini, and Arman Cohan. See my Vitæ page for details.
Publications
Peer-Reviewed
2026
CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA
Hanseok Oh, Parishad BehnamGhader, Benno Krojer, Hyunji Lee, Paul Liang, Siva Reddy, Verna Dankers
ECCV 2026
A History-Aware Visually Grounded Critic for Computer Use Agents
Jaewoo Lee, Zaid Khan, Archiki Prasad, Justin Chih-Yao Chen, Supriyo Chakraborty, Kartik Balasubramaniam, Sambit Sahu, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal
Findings of EMNLP 2026
Debug or Regenerate? Test-Guided Selection for LLM Code Repair
Atharv Kulkarni, Archiki Prasad, Vivek Srikumar, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal
Findings of EMNLP 2026
Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution
Nithin Sivakumaran, Shoubin Yu, Hyunji Lee, Yue Zhang, Ali Payani, Mohit Bansal, Elias Stengel-Eskin
Findings of EMNLP 2026
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
Ziyang Wang*, Yue Zhang*, Shoubin Yu, Ce Zhang, Zengqi Zhao, Jaehong Yoon, Hyunji Lee, Gedas Bertasius, Mohit Bansal
COLM 2026
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Hanqi Xiao*, Vaidehi Patil*, Zaid Khan, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansal
COLM 2026
Multimodal Fact-Level Attribution for Verifiable Reasoning
David Wan*, Han Wang*, Ziyang Wang, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal
ICML 2026
Generalized correctness models: Learning calibrated and model-agnostic correctness predictors from historical patterns
Hanqi Xiao, Vaidehi Patil, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansal
ICML 2026
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Jiyeon Kim*, Hyunji Lee*, Dylan Zhou*, Sue Hyun Park, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Sungmin Cha, Minjoon Seo
ACL 2026
Gistify! Codebase-Level Understanding via Runtime Execution
Hyunji Lee*, Minseon Kim, Chinmay Singh, Matheus Pereira, Atharv Sonwane, Isadora White, Elias Stengel-Eskin, Mohit Bansal, Zhengyan Shi, Alessandro Sordoni, Marc-Alexandre Côté, Xingdi Yuan, Lucas Caccia*
ICLR 2026
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
Hyunji Lee, Seunghyun Yoon, Yunjae Won, Hanseok Oh, Geewook Kim, Trung Bui, Franck Dernoncourt, Elias Stengel-Eskin, Mohit Bansal, Minjoon Seo
EACL 2026 Oral
2025
Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling
Hyunji Lee, Wenhao Yu, Hongming Zhang, Kaixin Ma, Jiyeon Kim, Dong Yu, Minjoon Seo
EMNLP BabyLM Workshop 2025
COrg: Generating Answers from Complex, Interrelated Contexts
Hyunji Lee, Franck Dernoncourt, Trung Bui, Seunghyun Yoon
NAACL 2025
How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
Seongyun Lee*, Geewook Kim*, Jiyeon Kim*, Hyunji Lee, Hoyeon Chang, Sue Hyun Park, Minjoon Seo
ICLR 2025
Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
Jiyeon Kim*, Hyunji Lee*, Hyowon Cho, Joel Jang, Hyeonbin Hwang, Seungpil Won, Youbin Ahn, Dohaeng Lee, Minjoon Seo
ICLR 2025 Oral
Best Paper, Towards Knowledgeable Foundation Models @AAAI 2025 Workshop
RouterRetriever: Exploring the Benefits of Routing over Multiple Expert Embedding Models
Hyunji Lee, Luca Soldani, Arman Cohan, Minjoon Seo, Kyle Lo
AAAI 2025
2024
Exploring the practicality of generative retrieval on dynamic corpora
Chaeeun Kim*, Soyoung Yoon*, Hyunji Lee, Joel Jang, Minjoon Seo
EMNLP 2024
Semiparametric Token-Sequence Co-Supervision
Hyunji Lee*, Doyoung Kim*, Jihoon Jun, Sejune Joo, Joel Jang, Kyung-Woon On, Minjoon Seo
ACL 2024
InstructIR: A Benchmark for Instruction Following of Information Retrieval Models
Hanseok Oh, Hyunji Lee, Seonghyeon Ye, Haebin Shin, Hansol Jang, Changwook Jun, Minjoon Seo
ACL KnowledgeNLP Workshop 2024 Oral
Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis
Sohee Yang, Jonghyeon Kim, Joel Jang, Seonghyeon Ye, Hyunji Lee, Minjoon Seo
TACL 2024
How Well Do Large Language Models Truly Ground?
Hyunji Lee*, Sejune Joo*, Chaeeun Kim, Joel Jang, Doyoung Kim, Kyung-Woon On, Minjoon Seo
NAACL 2024 Oral
Best Student Paper, Knowledge-Augmented NLP Workshop @ACL 2024
KTRL+F: Knowledge-Augmented In-Document Search
Hanseok Oh*, Haebin Shin*, Miyoung Ko, Hyunji Lee, Minjoon Seo
NAACL 2024
2023
Local 3D Editing via 3D Distillation of CLIP Knowledge
Junha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee, Jaegul Choo
CVPR 2023
Nonparametric Decoding for Generative Retrieval
Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vlad Karpukhin, Yi Lu, Minjoon Seo
Findings of ACL 2023
2022
Generative Multi-hop Retrieval
Hyunji Lee, Sohee Yang, Hanseok Oh, Minjoon Seo
EMNLP 2022 Oral
Finalist, Qualcomm Innovation Fellowship 2023
2021
Cost-effective End-to-end Information Extraction for Semi-structured Document Images
Wonseok Hwang, Hyunji Lee, Jinyeong Yim, Geewook Kim, Minjoon seo
EMNLP 2021 (short)
Preprint
2026
MINTEVAL: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Hyunji Lee*, Justin Chih-Yao Chen*, Joykirat Singh, Zaid Khan, Elias Stengel-Eskin, Mohit Bansal
Preprint
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
Joykirat Singh, Zaid Khan, Archiki Prasad, Justin Chih-Yao Chen, Akshay Nambi, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansall
Preprint
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
Duy Nguyen, Hanqi Xiao, Archiki Prasad, Zaid Khan, Anirban Das, Austin Zhang, Sambit Sahu, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansal
Preprint
Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
Duy Nguyen, Hanqi Xiao, Archiki Prasad, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal
Preprint
MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
Han Wang*, David Wan*, Hyunji Lee*, Thinh Pham, Mikaela Cankosyan, Weiyuan Chen, Elias Stengel-Eskin, Tu Vu, Mohit Bansal
Preprint
2025
BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills
Atharv Sonwane*, Isadora White*, Hyunji Lee, Matheus Pereira, Lucas Caccia, Minseon Kim, Zhengyan Shi, Chinmay Singh, Alessandro Sordoni, Marc-Alexandre Côté, Xingdi Yuan
Preprint
Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization
Yunjae Won, Hyunji Lee, Hyeonbin Hwang, Minjoon Seo
Preprint
2023
Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders
Hyunji Lee, Luca Soldani, Arman Cohan, Minjoon Seo, Kyle Lo
Preprint
Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment
Yongrae Jo, Seongyun Lee, Aiden SJ Lee, Hyunji Lee, Hanseok Oh, Minjoon Seo
Preprint