Presenting TIS (Token Importance Scoring) - A new way to compress KV cache

I see the combined benchmark as interesting, but not central to my current work. My main focus is upstream admission control: deciding which evidence/state should enter the model context before prefill. From that perspective, KV-cache compression is a downstream optimization for cases where long prefill has already happened or cannot be avoided. So I would not currently prioritize implementing TIS integration myself. It is a valid experiment, but it addresses a different intervention point. If Phase 4 of TIS moves in that direction, I would be interested to see whether it adds measurable value on top of upstream evidence/state selection. But for DESi, the primary question remains: can we avoid unnecessary context admission in the first place?