HFEPX · Eval paper review
Libo Sun, Po-wei Harn, Peixiong He, Xiao Qin
Published
May 14, 2026
Citations
0
Trust level
Provisional
Usefulness score
Unavailable
Extraction confidence
0% (Provisional)
Derived from abstract and metadata only.
Signals refreshed
May 17, 2026
Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.
This page is a lightweight research summary built from the abstract and metadata while deeper extraction catches up.
All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.
Best use
Background context only
Use if you need
A provisional background reference while structured extraction finishes.
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Main weakness
This page is still relying on abstract and metadata signals, not a fuller protocol read.
Eval-fit score is unavailable until extraction completes.
If you are doing eval pipeline work, start here
KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring. We study seven mechanisms across these five families under matched mean cache on long-form mathematical reasoning (MATH-500~\cite{hendrycks2021math}) with two distilled-reasoning models (Qwen-7B and Llama-8B variants of DeepSeek-R1-Distill~\cite{deepseek2025r1}) at budgets $b \in \{64, 128\}$. All seven were rejected. We then propose $α$, a one-function modification to the TriAttention~\cite{mao2026triattention} retention scorer that replaces argmax-top-$k$ with greedy facility-location-inspired selection under a V-space redundancy penalty controlled by a single weight $λ$. A pre-registered protocol tunes $λ$ on a frozen development split and confirms on a disjoint held-out split; with $λ= 0.5$, $α$ clears Bonferroni on two of the four (model, budget) cells (Qwen $b{=}128$ and Llama $b{=}64$), no cell is significantly negative, and the pre-registered Branch~A triggers. The finding is asymmetric: a minimal scoring modification beat heavier structural redesigns in this regime, and the combined matched-memory, sympy-graded, held-out confirmation protocol is the evidence standard that made the asymmetry visible.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
None explicit
No explicit feedback protocol extracted.
"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring."
None explicit
Validate eval design from full paper text.
"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring."
Not reported
No explicit QC controls found.
"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring."
Not extracted
No benchmark anchors detected.
"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring."
Not extracted
No metric anchors detected.
"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring."
Unknown
Rater source not explicitly reported.
"KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring."
This page is using abstract-level cues only right now. Treat the signals below as provisional.
Evaluation fields are inferred from the abstract only.
KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
