Storaï, Romain (로망)
Thesis: Targeting Token Complexity in Transformers during Inference
Alumni (M.S.)
Department of Computer Science and Engineering
Research Interests
- Adaptive Computation
- LLM Inference
Education
- M.S. in Computer Science and Engineering, Seoul National University 2023~2025
- M.Eng. in Computer Science (Dual Degree), IMT Mines Alès (France) 2021~2025
Publications
- Smarter, Not Harder: Training-Free Adaptive Computation for Transformers, Findings of ACL 2025
{Romain Storaï, Jaeseong Lee}, Seung-won Hwang. - HARP: Hesitation-Aware Reframing in Transformer Inference Pass, NAACL 2025
Romain Storaï, Seung-won Hwang. - Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation, Findings of EMNLP 2024
Jongho Kim, Romain Storaï, Seung-won Hwang.