Low-Rank Attention Residuals
Attention Residuals (AttnRes) replace the fixed residual sum with depth-wise attention over previous sub-layer outputs in Large Language Models (LLMs), but use each output as both a full-dimensional key and value. This couples routing with representation and makes the cost of computing depth-routing scores scale with hidden width $d$. We propose Low-Rank Attention Residuals (LR-AttnRes), which keep full-dimensional residual values while using $r$-dimensional keys, with $r < d$, for routing. LR-AttnRes uses the last $r$ dimensions of each value as the routing key, reducing total residual-side FLOPs while still improving performance. Comprehensive sweeps across the number of blocks ($N$) an...
| Authors | Jonathan Su |
|---|---|
| Primary category | cs.LG |
| Published | 19 June 2026 |
| Last updated at source | 22 September 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- RikkaBotan/LR-AttnRes-BERT-tinyModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.