Logan Markewich

原始摘录

Static embedding models can seem like a cheat code at first glance. Embedding a line of text is just a table lookup plus an average calculation. This translates to about 0.05 ms per text line on CPU, no transformer forward pass, it's WASM-friendly, and ~100× faster than even a small dense model.

Logan Markewich·2026年8月26日

此片段未附更多上下文，请阅读原始访谈。

位置来自原始文本；请结合原文语境核对措辞与归属。

原始摘录

A better teacher is not a better student. When the student is too small to absorb what the teacher knows (i.e. a small conv model), teacher quality stops mattering.

Logan Markewich·2026年8月26日

此片段未附更多上下文，请阅读原始访谈。

位置来自原始文本；请结合原文语境核对措辞与归属。

原始摘录

Don't score raw static token vectors with MaxSim. It's worse than the standard pooling, the scoring method is technically changing the training target. MaxSim assumes contextualized vectors and static embeddings are not contextual.

Logan Markewich·2026年8月26日

此片段未附更多上下文，请阅读原始访谈。

位置来自原始文本；请结合原文语境核对措辞与归属。