LLM Digest

Story

arxiv_cs_ai · Oct 30, 2026 · paper

Source brief

Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention

arxiv.orgOct 30, 2026
original source linked

In brief

Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context windows. However, at ultra-long context (above 1M tokens), full attent...

Feed lens

agentic

Read the original at arxiv.org →Open in live feed Read that day’s brief

Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention

Earlier in this thread 4 items

Subquadratic Attention with a Hierarchical Tree-Structured Indexer

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents

Causal Attention on CPU: A Cache-Aware and Load-Balanced Scheduling Kernel for Prefill

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness