arxiv:2502.14866
Guangxuan Xiao
Guangxuan-Xiao
AI & ML interests
Efficient Machine Learning
Recent Activity
authored
a paper
2 days ago
LServe: Efficient Long-sequence LLM Serving with Unified Sparse
Attention
authored
a paper
4 months ago
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and
Streaming Heads
upvoted
a
paper
4 months ago
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and
Streaming Heads
Organizations
Papers
11
models
7
Guangxuan-Xiao/fastcomposer-models
Updated
Guangxuan-Xiao/cat_quatitative_imgs
Updated
Guangxuan-Xiao/partial-coderanker-t5
Text Classification
•
Updated
•
186
Guangxuan-Xiao/coderanker
Text Classification
•
Updated
•
183
Guangxuan-Xiao/partial-coderanker
Text Classification
•
Updated
•
187
Guangxuan-Xiao/gpt-neo-1.3B-apps
Text Generation
•
Updated
•
119
Guangxuan-Xiao/gpt-neo-125M-apps
Text Generation
•
Updated
•
163