she/her
Hi!π
Iβm a PhD student in Computer Science and Engineering at UC San Diegoπ΄βοΈππ»ββοΈπ, advised by Prithviraj in the PEARLS Labπ§.
My research centers on building AI agentsπ€ that can understand and act over long-context inputs, with a focus on multimodal and embodied settings.
Iβm particularly interested in how agents can perform complex and long-horizon tasks that require interacting with environments over extended periods in ways that, while natural for humans, remain challenging for machines.
The broader goal of my work is to develop memory-augmented agents capable of reasoning, planning, and adapting across time with rich contextual information.
I began my research journey in natural language processing and generative AI, especially in leveraging LLMs for knowledge extraction. Iβve had the opportunity to apply this work during internships at AWS AI Lab, Megaton Labs, and Ancestry, where I focused on LLM-based structured information extraction.
Before UCSD, I worked as a software engineer on the Query Understanding team at Coupang (the largest e-commerce company in Korea), developing recommendation systems using large-scale user behavior data and product descriptions. I hold a B.S. and M.S. in Computer Science and Engineering from Sogang University.
SYMPTOMIFY: Transforming Symptom Annotations with Language Model Knowledge Harvesting. Bosung Kim and Ndapa Nakashole. 2023. (EMNLP Findings 2023) ππ»
Zero-shot Triplet Extraction by Template Infilling. Bosung Kim, Hayate Iso, Nikita Bhutani, Estevam Hruschka, Ndapa Nakashole, and Tom Mitchell. 2023. (IJCNLP-AACL 2023) ππ»
Chride at SemEval-2023 Task 10: Fine-tuned DebertaV3 on Detection of Online Sexism with Hierarchical Loss. Letian Peng and Bosung Kim. 2023. (ACL 2023 SemEval Workshop) ππ»
Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection. Bosung Kim and Ndapa Nakashole. 2022. (ACL 2022 BioNLP Workshop) ππ»
Query Reformulation for Descriptive Queries of Jargon Words Using a Knowledge Graph based on a Dictionary. Bosung Kim, Hyewon Choi, Haeun Yu, and Youngjoong Ko. 2021. (CIKM 2021) π
Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning. Bosung Kim*, Juae Kim*, Youngjoong Ko, and Jungyun Seo. 2020. (AAAI 2021) (*Equal contribution) ππ»
Multi-task learning for Knowledge Graph Completion using Pre-trained Language. Bosung Kim, Taesuk Hong, Youngjoong Ko, and Jungyun Seo. 2020. (COLING 2020) ππ»