三篇论文被ICML 2026接收

三篇关于高效推理、稀疏注意力和扩散大语言模型的论文被ICML'2026接收。

最近更新于 9月 15, 2026

被接收的论文如下：

  • Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse（由Zizhuo Fu主导）
  • TEAM: Temporal–Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration（由Linye Wei主导）
  • HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction（由Shengxuan Qiu、Haochen Huang主导）
会议