My primary research lies in the area of the sustainability and truthfulness of language models. I'm particularly interested in promising research avenues including:

• LLM Agents: LLMs interacting with environments using planning, memory, and tools.
• Efficient AI: Low latency and memory footprints of LLMs, while maintaining their performance on downstream tasks.
• Multimodal Reasoning: Comprehensive cognition over languages, vision, audio, time, etc.

홈페이지  https://lilab.hufs.ac.kr

주요 논문

( * denotes equal contribution)

[2025]

• Yerim Oh, Jun-Hyung Park, Junho Kim, SungHo Kim, SangKeun Lee. Incorporating Domain Knowledge into Materials Tokenization. ACL 2025.

• Nayeon Kim*, Eojin Jeon*, Jun-Hyung Park, SangKeun Lee. Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning. PAKDD 2025.

• Mingyu Lee, Junho Kim, Jun-Hyung Park, SangKeun Lee. Continual Debiasing: A Bias Mitigation Framework for Natural Language Understanding Systems. ESWA.

[2024]

• Jun-Hyung Park, Yeachan Kim, Mingyu Lee, Hyuntae Park, SangKeun Lee. MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction. EMNLP 2024.

• Hyuntae Park*, Yeachan Kim*, Jun-Hyung Park, SangKeun Lee. Zero-shot Commonsense Reasoning over Machine Imagination. Findings of EMNLP 2024.

• Junho Kim*, Yeachan Kim*, Jun-Hyung Park, Yerim Oh, Suho Kim, SangKeun Lee. MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science. Findings of EMNLP 2024.

• Jun-Hyung Park*, Hyuntae Park*, Yeachan Kim, Woosang Lim, SangKeun Lee. Moleco: Molecular Contrastive Learning with Chemical Language Models for Molecular Property Prediction. EMNLP 2024 Industry.

• Yeachan Kim, Jun-Hyung Park, SungHo Kim, Juhyeong Park, Sangyun Kim, SangKeun Lee. SEED: Semantic Knowledge Transfer for Language Model Adaptation to Materials Sciences. EMNLP 2024 Industry.

• Jun-Hyung Park, Mingyu Lee, Junho Kim, and SangKeun Lee. Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models. Findings of ACL 2024.

[2023]

• Jun-Hyung Park, Mingyu Lee, Junho Kim, and SangKeun Lee. Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models. Findings of ACL 2024.

• Jun-Hyung Park*, Hyuntae Park*, Youjin Kang, Eojin Jeon, and SangKeun Lee. DIVE: Towards Descriptive and Diverse Visual Commonsense Generation. EMNLP 2023.

• Yeachan Kim, Junho Kim, Jun-Hyung Park, Mingyu Lee, and SangKeun Lee. Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing. EMNLP 2023.

• Joon-Young Choi, Junho Kim, Jun-Hyung Park, Wing-Lam Mok, and SangKeun Lee. SMoP: Towards Efficient and Effective Prompt Tuning with Sparse Mixture-of-Prompts. EMNLP 2023.

• Yeachan Kim*, Junho Kim*, Wing-Lam Mok, Jun-Hyung Park and SangKeun Lee. Client-Customized Adaptation for Parameter-Efficient Federated Learning. Findings of ACL 2023.

• Jun-Hyung Park, Yeachan Kim, Junho Kim, Joon-Young Choi, and SangKeun Lee. Dynamic Structure Pruning for Compressing CNNs. AAAI 2023.

[2022]

• Jun-Hyung Park*, Mingyu Lee*, Junho Kim, Kang-Min Kim, and SangKeun Lee. Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking. EMNLP 2022.

• Jun-Hyung Park*, Junho Kim*, Mingyu Lee, Wing-Lam Mok, Joon-Young Choi, and SangKeun Lee. Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network. EMNLP 2022.

• Jun-Hyung Park*, Nayeon Kim*, Joon-Young Choi, Eojin Jeon, Youjin Kang, and SangKeun Lee. Break it Down into BTS: Basic, Tiniest Subword Units for Korean. EMNLP 2022.

• Jun-Hyung Park, Kang-Min Kim, and SangKeun Lee. Quantized Sparse Training: A Unified Trainable Framework for Joint Pruning and Quantization of DNNs. ACM TECS.

• Jun-Hyung Park*, Yong-Ho Jung*, Joon-Young Choi, Mingyu Lee, Junho Kim, Kang-Min Kim, and SangKeun Lee. Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference. Findings of ACL 2022. 

• Jun-Hyung Park, Byung-Ju Choi, and SangKeun Lee. Examining the Impact of Adaptive Convolution on Natural Language Understanding. ESWA.