Ítems similars

• Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?
  per: Abedsoltan, Amirhesam, et al.
  Publicat: (2025)
• The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
  per: Nawrot, Piotr, et al.
  Publicat: (2025)
• How Sparse Attention Approximates Exact Attention? Your Attention is Naturally $n^C$-Sparse
  per: Deng, Yichuan, et al.
  Publicat: (2024)
• Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
  per: Thangarasa, Vithursan, et al.
  Publicat: (2023)
• Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
  per: Yuan, Jingyang, et al.
  Publicat: (2025)