Get started
Author

Sunghyeon Woo

Observed name: Woo, Sunghyeon
OpenAlex ID: A5125939131
PaCA: Partial Connection Adaptation for Efficient Fine-Tuning
2025 · Woo, Sunghyeon, Namkung, Sol, et al. · arXiv (Cornell University) · 1
PDF
HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference
2025 · Inho Jeong, Sunghyeon Woo, et al. · neural information processing systems · 1
Activation Sharing with Asymmetric Paths Solves Weight Transport Problem without Bidirectional Connection
2021 · Sunghyeon Woo, Jeongwoo Park, et al. · neural information processing systems · 1
Carryover Drafting: Recycling Rejected States for Speculative Decoding
2026 · Koo, Jahyun, Woo, Sunghyeon, et al. · arXiv (Cornell University)
PDF
SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
2026 · Woo, Sunghyeon, Seo, Ahreum, et al. · arXiv (Cornell University)
PDF
ICaRus: Identical Cache Reuse for Efficient Multi Model Inference
2026 · Woo, Sunghyeon, Kil, Jaeeun, et al. · arXiv (Cornell University)
PDF
Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
2026 · Bae, Jeongin, Park, Baeseong, et al. · arXiv (Cornell University)
PDF
PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
2026 · Woo, Sunghyeon, Kim, Hoseung, et al. · arXiv (Cornell University)
PDF
Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
2026 · Lee, Jeongtae, Jo, Minjung, et al. · arXiv (Cornell University)
PDF
RAPA: Recursively Aligned Pathway Adaptation of Large Language Models
2026 · Sol Namkung, Sunghyeon Woo, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
2025 · Yoon, Kanghoon, Kim, Minsub, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count: 3
H-index: 1
I10-index:
Year
Topic
Type