α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Junxian Guo
Junxian Guo
4
papers
349
total citations
papers (4)
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
ICLR 2025
arXiv
179
citations
SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
ICLR 2025
arXiv
98
citations
XAttention: Block Sparse Attention with Antidiagonal Scoring
ICML 2025
arXiv
71
citations
SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference
ICCV 2025
arXiv
1
citations