most citedXAttention: Block Sparse Attention with Antidiagonal Scoring

1 citations · 1 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG2025

Optimizing Mixture of Block Attention

Guangxuan Xiao, Junxian Guo, Kasra Mazaheri +1

Mixture of Block Attention (MoBA) (Lu et al., 2025) is a promising building block for efficiently processing long contexts in LLMs by enabling queries to sparsely attend to a small…

cs.CV2025

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Samir Khaki, Junxian Guo, Jiaming Tang +6

Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analys…

cs.LG2025

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Samir Khaki, Xiuyu Li, Junxian Guo +7

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and…

cs.CL20251 cited

XAttention: Block Sparse Attention with Antidiagonal Scoring

Ruyi Xu, Guangxuan Xiao, Haofeng Huang +2

Long-Context Transformer Models (LCTMs) are vital for real-world applications but suffer high computational costs due to attention's quadratic complexity. Block-sparse attention mi…

cs.DC2025

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference

Zihan Liu, Xinhao Luo, Junxian Guo +11

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cac…

cs.CL2025

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Shang Yang, Junxian Guo, Haotian Tang +7

Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due…