arxiv:2502.14866
Song
songhan
AI & ML interests
efficient AI computing
Recent Activity
authored
a paper
about 10 hours ago
LServe: Efficient Long-sequence LLM Serving with Unified Sparse
Attention
upvoted
a
paper
3 months ago
NVILA: Efficient Frontier Visual Language Models
authored
a paper
7 months ago
Wolf: Captioning Everything with a World Summarization Framework
Organizations
Papers
10
models
None public yet
datasets
None public yet