MoEUT: Mixture-of-Experts Universal Transformers

Documenti analoghi

• SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
  di: Csordás, Róbert, et al.
  Pubblicazione: (2023)
• Do Language Models Use Their Depth Efficiently?
  di: Csordás, Róbert, et al.
  Pubblicazione: (2025)
• Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
  di: Csordás, Róbert, et al.
  Pubblicazione: (2024)
• Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space
  di: Liu, Houjun, et al.
  Pubblicazione: (2025)
• Attending to Graph Transformers
  di: Müller, Luis, et al.
  Pubblicazione: (2023)