Papers

• Dropping the Anchor: Statistical Context Summarization for Distributed Systems via Pulsar Attention (2026)
  Aryan Sood et al.
  5.01
• GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference (2026)
  Vimal William et al.
  2.00
• CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention (2026)
  Yufei Xue et al.
  2.00
• Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling (2026)
  Xiang Hu et al.
  2.00
• Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE (2026)
  Haozhan Tang et al.
  2.00
• Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (2026)
  Tommaso Cerruti et al.
  2.00
• Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity (2026)
  Loïc Cabannes et al.
  1.94
• LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget (2026)
  Changhai Zhou et al.
  1.94
• Periodic RoPE for Infinite Context LLMs (2026)
  Simin Huo
  1.89
• Fast-dLLM v2: Efficient Block-Diffusion LLM (2025)
  Chengyue Wu et al.
  1.28