31 Matching Annotations
  1. Apr 2026
    1. V3.3 achieves 70.4% in Mode A (zero-LLM), with +23.8pp on multi-hop and +12.7pp on adversarial. V3.2 achieved 74.8% Mode A and 87.7% Mode C; the 4.4pp gap reflects a deliberate architectural trade-off.

      在零LLM模式下仅比有LLM支持的模式低17.3%,这一结果令人震惊。这表明生物启发的记忆架构可能比我们想象的更强大,能够在没有大型语言模型支持的情况下保持大部分性能,挑战了'强大AI必须依赖大型模型'的主流观点。

  2. Feb 2025
  3. Aug 2023
  4. Jul 2023
    1. Based on experienceand knowledge, they try to connect fevers, headaches, runny noses, and stomachpains to various diseases. In other words, the Columbia and Microsoftresearchers wrote a groundbreaking study by utilizing the natural, obviousmethodology that everybody uses to make health diagnoses.
  5. Mar 2021
  6. Jan 2021
  7. Oct 2020
  8. Sep 2020
  9. Aug 2020
  10. Jul 2020
  11. Jun 2020