AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Gradient Intrinsic Dimensionality Alignment:Narrowing The Gap Between Low-Rank Adaptation and Full Fine-Tuning

Jingqi Ye, haonan he, Minglei Li, Fujun Han, Tao Chen, Peng Ye

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
align LoRA rank with gradient intrinsic dimensionality and reallocate across layers (RaLoRA-Pro)LoRA · GLUE average (T5-Base)accuracy: 82.08 -> 87.23Improved
align LoRA rank with gradient intrinsic dimensionality (RaLoRA)LoRA · GSM8K (LLaMA-3.1-8B)accuracy: 67.78 -> 72.25Improved
align LoRA rank with gradient intrinsic dimensionality (RaLoRA)LoRA · HumanEval (LLaMA-3.1-8B)pass@1: 43.09 -> 48.78Improved
add inter-layer reallocation on top of alignment (RaLoRA-Pro)LoRA · MT-Bench (LLaMA-3.1-8B)score: 6.15 -> 6.72Improved
RaLoRA alignment on CLIP image classificationLoRA · Image classification average (CLIP-ViT-B/16)accuracy: 89.08 -> 90.53Improved
use entropy-based estimator instead of SVD threshold 1e-3 (ablation)RaLoRA · GSM8Kaccuracy: 70.64 -> 72.25Improved
use entropy-based estimator instead of SVD threshold 1e-1 (ablation)RaLoRA · HumanEvalpass@1: 45.53 -> 48.78Improved
add intra-layer GID alignment to loss-sensitivity reallocation (LS-LoRA to RaLoRA-Pro, rank 8) (ablation)LS-LoRA · HumanEvalpass@1: 39.83 -> 46.95Improved
add GID alignment to LoRA at rank 64 (ablation)LoRA · GSM8Kaccuracy: 67.17 -> 74.55Improved
add inter-layer reallocation to RaLoRA at rank 64 (ablation)RaLoRA · GSM8Kaccuracy: 74.55 -> 75.23Improved
increase max expansion factor nmax from 16 to 64 (ablation)RaLoRA · GSM8K / HumanEvalaccuracy / pass@1: GSM8K 72.25 -> 71.19; HumanEval 45.12 -> 48.78Mixed
widen rank reallocation range from 8-8 to 4-32 (ablation)RaLoRA-Pro · MT-Bench / GSM8Kscore / accuracy: MT-Bench 6.19 -> 6.70; GSM8K 71.42 -> 71.39Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy