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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
method 2polarities
use method 2representative citing papers
A benchmark across 156 comparisons finds classical ML models win 116 times while larger pretrained and LLM models win far fewer, showing predictive performance depends on model-task fit rather than scale.
citing papers explorer
-
BoostLoRA: Growing Effective Rank by Boosting Adapters
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.
-
Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction
A benchmark across 156 comparisons finds classical ML models win 116 times while larger pretrained and LLM models win far fewer, showing predictive performance depends on model-task fit rather than scale.