| Seasonal-adjustment based feature selection method for predicting epidemic with large-scale search engine logs TQ Tran, J Sakuma Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019 | 19 | 2019 |
| Unsupervised causal binary concepts discovery with vae for black-box model explanation TQ Tran, K Fukuchi, Y Akimoto, J Sakuma Proceedings of the AAAI Conference on Artificial Intelligence 36 (9), 9614-9622, 2022 | 9 | 2022 |
| Stepwise alignment for constrained language model policy optimization A Wachi, T Tran, R Sato, T Tanabe, Y Akimoto Advances in Neural Information Processing Systems 37, 104471-104520, 2025 | 4 | 2025 |
| Statistically significant pattern mining with ordinal utility TQ Tran, K Fukuchi, Y Akimoto, J Sakuma Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020 | 4 | 2020 |
| Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing TQ Tran, A Wachi, R Sato, T Tanabe, Y Akimoto arXiv preprint arXiv:2502.02153, 2025 | | 2025 |
| 対話モデルに対する敵対的プロンプトの効率的な最適化 JS Kazuki Yano, Koki Wataoka, Thien Q. Tran, Tsubasa Takahashi, Seng Pei Liew 言語処理学会第30回年次大会(NLP2024), 2024 | | 2024 |
| Constitutional AIにおけるセーフティアラインメントの改善 TT Koki Wataoka*, Thien Q. Tran*, Wakana Maeda 言語処理学会第30回年次大会(NLP2024), 2024 | | 2024 |
| モデル介入を用いる Jailbreak prompt 攻撃の初期応答の選択手法 TT Thien Q. Tran, Koki Wataoka 言語処理学会第30回年次大会(NLP2024), 2024 | | 2024 |
| Vulnerabilities Mitigation for Safety-Aligned Language Models via Debiasing TQ Tran, A Wachi, R Sato, T Tanabe, Y Akimoto | | |
| Initial Response Selection for Prompt Jailbreaking using Model Steering TQ Tran, K Wataoka, T Takahashi ICLR 2024 Workshop on Secure and Trustworthy Large Language Models, 0 | | |
Youhei AkimotoUniversity of TsukubaПідтверджена електронна адреса в cs.tsukuba.ac.jp
