Guangxuan Xiao

~Guangxuan_Xiao1

6

论文总数

3.0

年均投稿

6.4

平均评分

接收情况6/6

会议分布

ICLR

3

NeurIPS

2

ICML

1

发表论文 (6 篇)

20253 篇

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

ICLR 2025Poster

XAttention: Block Sparse Attention with Antidiagonal Scoring

ICML 2025Poster

Retrieval Head Mechanistically Explains Long-Context Factuality

20243 篇

Efficient Streaming Language Models with Attention Sinks

ICLR 2024Poster

BitDelta: Your Fine-Tune May Only Be Worth One Bit

NeurIPS 2024Poster

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory

NeurIPS 2024Poster

合作者 (20)

Chaojun Xiao1 篇

Maosong Sun1 篇

Pengle Zhang1 篇

Yankai Lin1 篇

Zhengyan Zhang1 篇