publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2025
- Beyond Line-Level Filtering for the Pretraining Corpora of LLMsOct 2025
- Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding KoreanOct 2025
- Thunder-Tok: Minimizing Tokens per Word in Tokenizing Korean Texts for Generative Language ModelsJun 2025
- Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal ResourcesJun 2025
- Enhancing Face Recognition Accuracy for Under-Display Cameras via Image RestorationIn SID Symposium Digest of Technical Papers, Jun 2025To appear. (Distinguished Paper, Top 5%)
- Investigating the Effects of Degradation and Restoration on Face Recognition in Under-Display CamerasJournal of the Society for Information Display, May 2025
- UDC-VIT: A Real-World Video Dataset for under-Display CamerasIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2025To appear
- Integrating Spatial and Frequency Information for Under-Display Camera Image RestorationJan 2025
2024
- Exploring the Impact of Pretraining Corpora on the Performance of Language ModelsIn Korea Computer Congress, Jun 2024
- Analysis of Large Language Model Performance According to Korean-English Training Data Ratio in Continual LearningIn Korea Software Congress, Dec 2024
2023
- Applying Influence Range to Under-Display Camera Image RestorationIn Proceedings of the 23rd International Meeting on Information Display (IMID), Dec 2023Poster
- UDC-SIT: A Real-World Dataset for under-Display CamerasIn Proceedings of the 37th International Conference on Neural Information Processing Systems, Dec 2023