Scholar
Seojin Kim
Google Scholar ID: gFpnvWEAAAAJ
Seoul National University(SNU), KAIST
Citations & Impact
Citations
30
H-index
3
i10-index
1
Publications
8
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- [{'Title': 'Training Text-to-Molecule Models with Context-Aware Tokenization', 'Authors': 'Seojin Kim, Hyeontae Song, Jaehyun Nam, Jinwoo Shin', 'Conference': 'EMNLP, 2025 (findings), NeurIPS Workshop on AI for New Drug Modalities (NeurIPSW-AIDrugX), 2024'}, {'Title': 'FontAdapter: Instant Font Adaptation in Visual Text Generation', 'Authors': 'Myungkyu Koo, Subin Kim, Sangkyung Kwak, Jaehyun Nam, Seojin Kim, Jinwoo Shin', 'Conference': 'Preprint, 2025'}, {'Title': 'Mamba Drafters for Speculative Decoding', 'Authors': 'Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Kyuyoung Kim, Woomin Song, Seojin Kim, Insoo Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati', 'Conference': 'EMNLP, 2025 (findings), ICML Workshop on Efficient Systems for Foundation Models (ICMLW-ES-FoMo), 2025'}, {'Title': 'Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness', 'Authors': 'Suhyeok Jang, Seojin Kim, Jinwoo Shin, Jongheon Jeong', 'Conference': 'TMLR, 2024'}, {'Title': 'Data-Efficient Molecular Generation with Hierarchical Textual Inversion', 'Authors': 'Seojin Kim, Jaehyun Nam, Sihyun Yu, Younghoon Shin, Jinwoo Shin', 'Conference': 'ICML, 2024, NeurIPS Workshop on New Frontiers of AI for Drug Discovery and Development (NeurIPSW-AI4D3), 2023'}, {'Title': 'Fragment-based Multi-view Molecular Contrastive Learning', 'Authors': 'Seojin Kim, Jaehyun Nam, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin', 'Conference': 'TMLR, 2024, ICLR Workshop on Machine Learning for Materials (ICLRW-ML4Materials), 2023'}, {'Title': 'Confidence-aware Training of Smoothed Classifiers for Certified Robustness', 'Authors': 'Jongheon Jeong, Seojin Kim, Jinwoo Shin', 'Conference': 'AAAI, 2023 (Oral), ECCV Workshop on Adversarial Robustness in the Real World (ECCVW-AROW), 2022'}]
Research Experience
- No specific research experience information provided.
Background
- Research Interests: Efficiently adapting large language models for domain-specific applications such as drug discovery, accelerated inference, and visual image generation. Fields: Artificial Intelligence, Chemistry, Computer Science, Mathematics.
Miscellany
- No other information provided.
Co-authors