pith. sign in

MELoRA: Mini-ensemble low-rank adapters for parameter- efficient fine-tuning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 2

polarities

background 2

representative citing papers

BoostLoRA: Growing Effective Rank by Boosting Adapters

cs.LG · 2026-04-30 · unverdicted · novelty 7.0

BoostLoRA grows effective adapter rank linearly via iterative boosting on hard examples with orthogonal low-rank updates, outperforming both single-shot ultra-low-rank adapters and full fine-tuning on math and code tasks with zero added inference overhead.

citing papers explorer

Showing 2 of 2 citing papers.

  • BoostLoRA: Growing Effective Rank by Boosting Adapters cs.LG · 2026-04-30 · unverdicted · none · ref 28

    BoostLoRA grows effective adapter rank linearly via iterative boosting on hard examples with orthogonal low-rank updates, outperforming both single-shot ultra-low-rank adapters and full fine-tuning on math and code tasks with zero added inference overhead.

  • Not How Many, But Which: Parameter Placement in Low-Rank Adaptation cs.LG · 2026-05-12 · unverdicted · none · ref 70

    Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.