Jeongin Bae
~Jeongin_Bae1
4
论文总数
4.0
年均投稿
平均评分
接收情况1/4
会议分布
ICLR
3
NeurIPS
1
发表论文 (4 篇)
20254 篇
4
CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
NeurIPS 2025Poster
4
To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability
ICLR 2025Rejected
5
Don’t Discard, but Keep It Small: Context-Preserving KV Cache Compression with Importance-Aware Adaptive Precision
ICLR 2025Rejected
5
FlexBCQ: Flexible Binary-coding Quantization for Large Language Models
ICLR 2025Rejected