News
- May 19, 2026 β Our new NVIDIA project, How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning, is now on arXiv.
- Feb 23, 2026 β Joined the NVIDIA Research LACR team as a PhD research intern.
- Jun 23, 2025 β Started my PhD research internship at Microsoft Research in Redmond.
- May 22, 2025 β Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning is now on arXiv.
- Jun 24, 2024 β Started my internship at AWS AI Lab in NYC π½.
Publications
How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning π π
Bosung Kim*, Ruiyi Wang*, David Acuna, Jaehun Jung, Alexander Trevithick, Brandon Cui, Yejin Choi, Prithviraj Ammanabrolu
arXiv preprint, 2026 Β· * equal contribution
DECADE: Evaluating Evolving Long-Term Memory in Personalized Conversational AI Assistants
Bosung Kim, Hao Cheng, Yuan Gao, Prithviraj Ammanabrolu, Michel Galley, Rachel Rong, Jianfeng Gao
Under review, 2026
Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning π π
Bosung Kim, Prithviraj Ammanabrolu
arXiv preprint, 2025
SYMPTOMIFY: Transforming Symptom Annotations with Language Model Knowledge Harvesting π
Bosung Kim, Ndapa Nakashole
EMNLP Findings, 2023
Zero-shot Triplet Extraction by Template Infilling π π
Bosung Kim, Hayate Iso, Nikita Bhutani, Estevam Hruschka, Ndapa Nakashole, Tom Mitchell
IJCNLP-AACL, 2023
Chride at SemEval-2023 Task 10: Fine-tuned DebertaV3 on Detection of Online Sexism with Hierarchical Loss π
Letian Peng, Bosung Kim
ACL SemEval Workshop, 2023
Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection π
Bosung Kim, Ndapa Nakashole
ACL BioNLP Workshop, 2022
Query Reformulation for Descriptive Queries of Jargon Words Using a Knowledge Graph based on a Dictionary π
Bosung Kim, Hyewon Choi, Haeun Yu, Youngjoong Ko
CIKM, 2021
Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning π
Bosung Kim*, Juae Kim*, Youngjoong Ko, Jungyun Seo
AAAI, 2021 Β· * equal contribution
Multi-task learning for Knowledge Graph Completion using Pre-trained Language π
Bosung Kim, Taesuk Hong, Youngjoong Ko, Jungyun Seo
COLING, 2020
Journal Articles
Novel Regularization Method for the Class Imbalance Problem π
Bosung Kim, Youngjoong Ko, Jungyun Seo
Expert Systems with Applications, 2022