SALT shows that a subspace-aligned domain centroid plus a rank-1 or rank-2 user residual can recover or exceed high-rank LoRA accuracy while cutting the per-adapter swap footprint by up to 16x.
Compress then Serve: Serving Thousands of Lo
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving
SALT shows that a subspace-aligned domain centroid plus a rank-1 or rank-2 user residual can recover or exceed high-rank LoRA accuracy while cutting the per-adapter swap footprint by up to 16x.