최승택 교수
- 학위
- Ph.D. in Computer Science, Yonsei University
- 연구분야
- Foundation Models, Multimodal Large Language Models, AI Evaluation
- 강의
- 기계학습의이해, 멀티모달개론, 정보검색및추천시스템
- 이메일
- seungtaek.choi@hufs.ac.kr
- 연구실
세부내용
최종학력
Ph.D. in Computer Science and Engineering, Yonsei University, Republic of Korea
경력사항
- Assistant Professor @ Division of Language & AI, Hankuk University of Foreign Studies
-
Member of Technical Staff @ Trillion Labs
-
Machine Learning Researcher @ Yanolja
- Research Scientist @ Riiid
-
Research Internship @ SKT T-Brain
주요 논문 및 저서
[Data-efficient Learning]
- (2026) TextME: Bridging Unseen Modalities Through Text Descriptions. ICML 2026.
- (2025) Trillion 7B Technical Report. arXiv 2025.
- (2025) Rethinking the Training Paradigm of Discrete Token-Based Multimodal LLMs: An Analysis of Text-Centric Bias. CIKM 2025.
- (2025) ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function. Machine Learning 2025.
- (2024) Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models. arXiv 2024.
- (2024) Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding. EMNLP 2024.
- (2024) Multi-Architecture Multi-Expert Diffusion Models. AAAI 2024.
- (2023) Addressing Negative Transfer in Diffusion Models. NeurIPS 2023.
- (2023) Addressing Cold Start Problem for End-to-end Automatic Speech Scoring. INTERSPEECH 2023.
- (2023) Cross Encoding As Augmentation: Towards Effective Educational Text Classification. Findings of ACL 2023.
- (2023) Towards Practical Plug-and-Play Diffusion Models. CVPR 2023.
- (2022) C²L: Causally Contrastive Learning for Robust Text Classification. AAAI 2022.
- (2021) Counterfactual Generative Smoothing for Imbalanced Natural Language Classification. CIKM 2021.
- (2021) Label and Context Augmentation for Response Selection at DSTC8. TASLP 2021.
- (2020) Conditional Response Augmentation for Dialogue using Knowledge Distillation. INTERSPEECH 2020.
- (2020) Less is More: Attention Supervision with Counterfactuals for Text Classification. EMNLP 2020.
- (2019) Counterfactual Attention Supervision. ICDM 2019.
[Evaluation of AI]
- (2025) Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge. CIKM 2025
- (2025) FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark. NAACL 2025.
- (2023) Evaluation of Question Generation Needs More References. Findings of ACL 2023.
- (2022) Evaluating the Knowledge Dependency of Questions. EMNLP 2022.
- (2018) Visual Choice of Plausible Alternatives: An Evaluation of Image-based Commonsense Causal Reasoning. LREC 2018.
[Knowledge-intensive Generative Systems]
- (2025) Overcoming Source Object Grounding for Semantic Image Editing. TACL 2025.
- (2023) Retrieval-augmented Instructional Video Encoding for Dense Video Captioning. Findings of ACL 2023.
- (2023) On Complementarity Objectives for Hybrid Retrieval. ACL 2023.
- (2022) Towards Compositional Generalization in Code Search. EMNLP 2022.
- (2022) Debiasing Event Understanding for Visual Commonsense Tasks. Findings of ACL 2022.
- (2021) Structure-Augmented Keyphrase Generation. EMNLP 2021.
- (2020) Retrieval-Augmented Controllable Review Generation. COLING 2020.
- (2019) MICRON: Multigranular Interaction for Contextualizing Representation in Non-factoid Question Answering. EMNLP 2019.
- (2018) Machine-translated Knowledge Transfer for Commonsense Causal Reasoning. AAAI 2018.