Seed

Headlines · 1

1. 6h
   ByteDance Seed ties long-context swings to chunked KV cache 'phase sensitivity'

   ByteDance's Seed team says in a new research paper that large language models' performance swings on very long inputs stem mainly from "phase sensitivity" introduced by chunked KV cache compression. To cut memory use in long-context inference, the method compresses consecutive token windows into fewer entries at a fixed stride, creating a new positional coordinate: a token's "phase" relative to the compression window boundary. Experiments show the same information becomes much harder or easier to retrieve at different phases, with long-context retrieval accuracy gaps of up to 40 percentage points in some large open-source models.

   AIbase AI新闻 · 🔥 8

Experience and discussion from the community

Share my Seed experienceAsk about Seed