Scholar
Sunghyeon Woo
Google Scholar ID: oGJyPGQAAAAJ
서울대학교
Deep learning
Neuromorphic algorithm
Memory efficient training
Activation compression
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
29
H-index
3
i10-index
1
Publications
5
Co-authors
0
Publications
6 items
Carryover Drafting: Recycling Rejected States for Speculative Decoding
2026
Cited
0
SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
2026
Cited
0
Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
2026
Cited
0
PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
2026
Cited
0
PaCA: Partial Connection Adaptation for Efficient Fine-Tuning
2025
Cited
0
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
arXiv.org · 2024
Cited
1
