Skip to content

Author

Seungjin Kim

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video

DeltaS is proposed, a query-agnostic, training-free method that retains video chunks inducing larger normalized state change, or state drift, in a controlled comparison with the budget and retention policy held fixed, which suggests that the two memories of hybrid architectures can work cooperatively.

Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.