Scholay

学术搜索 · AI 审稿 · LaTeX 协作

Jun Zhu

发表论文 38 篇 · 总被引 888 次 · h-index 15

代表论文

  • SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference (2025 · arXiv.org · 被引 111)
  • SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference (2025 · International Conference on Machine Learning · 被引 106)
  • SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training (2025 · arXiv.org · 被引 65)
  • Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency (2025 · arXiv.org · 被引 61)
  • SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention (2025 · arXiv.org · 被引 44)
  • SageAttention2++: A More Efficient Implementation of SageAttention2 (2025 · arXiv.org · 被引 28)