AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

A Better Start: Sensitivity-Aware Warm-Up for Robust and Efficient Fine-Tuning

Yile Chen, Zeyi Wen, Jian Chen, Jin Huang

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning

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
add SAWU to Adam fine-tuningAdam + linear warm-up · RoBERTa-base GLUE (6 tasks)test accuracy: e.g. QNLI 90.24 -> 92.62; CoLA 55.75 -> 63.12Improved
add SAWU to Adam fine-tuningAdam · MRPC (RoBERTa-base)test accuracy: 85.86 -> 87.59Improved
add SAWU to RAdamRAdam · QNLI (RoBERTa-base)test accuracy: 49.46 -> 91.78Improved
add SAWU to LAMBLAMB · MNLI (RoBERTa-base)test accuracy: 86.49 -> 86.37Hurt
add SAWU to AdamWAdamW · MNLI (RoBERTa-base)test accuracy: 83.85 -> 86.43Improved
add SAWU to LLaMA LoRA fine-tuningAdam · LLaMA-3.2-1B LoRA, avg of 4 GLUE tasksaccuracy: 89.72 -> 91.10Improved
add sensitivity-aware loss (ablation)vanilla warm-up Adam · MRPC (RoBERTa-base)warm-up phase accuracy: 76.06 -> 83.01Improved
add sensitivity-aware loss (ablation)vanilla warm-up Adam · MRPC (RoBERTa-base)decay phase accuracy: 85.86 -> 87.51Improved
add sensitivity-guided scheduling on top of loss (ablation)SAWU (+SL) · MRPC (RoBERTa-base)warm-up phase accuracy: 83.01 -> 82.96No clear effect
add adaptive phase transition (ablation)SAWU (+SL+SS) · MRPC (RoBERTa-base)training time (decay phase, s): 61 -> 60Improved
increase sliding window w to 9 (ablation)SAWU · MRPC (RoBERTa-base)warm-up accuracyHurt
set max count k to 3 instead of 7-9 (ablation)SAWU · MRPC (RoBERTa-base)warm-up accuracy: 67.99 for k=3Hurt

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