Hao Mark Chen

~Hao_Mark_Chen1

3

论文总数

3.0

年均投稿

5.9

平均评分

接收情况2/3

会议分布

ICLR

2

NeurIPS

1

发表论文 (3 篇)

20253 篇

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

NeurIPS 2025Poster

Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference

ICLR 2025Rejected

Progressive Mixed-Precision Decoding for Efficient LLM Inference

ICLR 2025Poster

合作者 (13)

Hongxiang Fan3 篇

Stylianos Venieris2 篇

Konstantin Mishchenko1 篇

Yiu Ka Fai Cedric1 篇

Masato Motomura1 篇