#Long Context

2026

• 07-30 EN

  Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool

• 07-30 中

  Libra 阅读笔记:用有界序列池驯服长上下文训练中的注意力负载偏斜

• 07-26 EN

  KV-Fold: Turning the KV Cache Into a Left Fold for Long-Context Inference

• 07-26 中

  KV-Fold：把 KV 缓存当作长上下文推理的左折叠累加器

• 07-15 EN

  COBS: What Block-Sparse Attention Selectors Are Actually Missing (A Second-Order Fix)

• 07-15 中

  COBS 阅读笔记:块稀疏注意力的选择器到底漏掉了什么(一个二阶修正)

• 07-05 EN

  Lynx: Progressive Speculative KV Cache Transfer for Disaggregated LLM Inference

• 07-05 中

  Lynx 阅读笔记：渐进式推测量化加速解聚合 LLM 推理的 KV 传输

• 07-04 EN

  MosaicKV: Dynamic Two-Dimensional KV Cache Compression for Long-Context LLM Serving — Technical Review

• 07-04 中

  MosaicKV：面向超长上下文LLM服务的动态二维KV缓存压缩——阅读笔记

• 06-24 EN

  SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

• 06-24 中

  SparDA：稀疏解耦注意力，让长上下文推理又快又准

• 06-22 EN

  MRAgent: Why Memory Should Be Reconstructed, Not Retrieved

• 06-22 中

  MRAgent：记忆应该被重建，而不是被检索

• 06-10 EN

  KeepKV: Lossless KV Cache Compression via Electoral Votes and ZIP-Merging

• 06-10 中

  KeepKV：用「选举票」机制和零扰动合并实现无损 KV 缓存压缩

• 03-29 EN

  Ring Attention: Blockwise Transformers for Near-Infinite Context — In-Depth Technical Review