ngocbh commited on
Commit
2d39dfa
·
verified ·
1 Parent(s): b124151

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -19,6 +19,9 @@ The core idea behind TRIM-KV is to learn the intrinsic importance of each key–
19
  The retention score is query-agnostic and captures the long-term utility of tokens. This is different from attention scores, which are query-dependent: they capture the short-term utility for predicting the next token and are recomputed at every step, making them local, myopic, and highly dependent on the transient decoding state.
20
 
21
 
 
 
 
22
  ### Why TRIM-KV?
23
 
24
  It's fast
 
19
  The retention score is query-agnostic and captures the long-term utility of tokens. This is different from attention scores, which are query-dependent: they capture the short-term utility for predicting the next token and are recomputed at every step, making them local, myopic, and highly dependent on the transient decoding state.
20
 
21
 
22
+ <a href="https://arxiv.org/pdf/2512.03324"><img src="https://img.shields.io/badge/arxiv-2512.03324-red?style=for-the-badge"></a>
23
+
24
+
25
  ### Why TRIM-KV?
26
 
27
  It's fast