Author

Maruthi Vemula

h-index 3 View on Semantic Scholar

We have 1 of 8 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.

Jul 2026

Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating

A language model with a bounded working memory must repeatedly decide which stored items to keep. Every deployed method decides the moment an item arrives, from the past (StreamingLLM, H2O) or from a guess about the future (SnapKV). We recast the choice as an estimation problem on a hidden signal, whether an item will...

Maruthi Vemula, Neeraja Gajula · arXiv.org · 0 citations