Jiwon Song | 송지원

LiteStage: Latency-aware Layer Skipping for Multi-stage Reasoning

Beomseok Kang, Jiwon Song, Jae-Joon Kim

arXiv preprint arXiv:2510.14211

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning

Jiwon Song, Dongwon Jo, Yulhwa Kim, Jae-Joon Kim

The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation

Dongwon Jo*, Jiwon Song*, Yulhwa Kim, Jae-Joon Kim

*Equal contribution

arXiv preprint arXiv:2502.01068

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Jiwon Song*, Kyungseok Oh*, Taesu Kim, Hyungjun Kim, Yulhwa Kim, Jae-Joon Kim

*Equal contribution

The 41st International Conference on Machine Learning (ICML 2024)