Junxian Guo

3

Papers

256

Total Citations

Papers (3)

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

SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference