AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models

Shilei Cao, Hehai Lin, Jiashun Cheng, Yang Liu, Guowen Li, Xuehe Wang, Juepeng Zheng, Haoyuan Liang, Meng Jin, Chengwei Qin, Hong Cheng, Haohuan Fu

ICLR 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
combine TADP and SFAS instead of either alone (ablation)WeatherPEFT · Downscaling T2mRMSE: 1.161 (SFAS only) -> 1.119Improved
add SFAS to TADP (versus TADP only) (ablation)WeatherPEFT · Regional precipitation 12hSEEPS: 0.549 -> 0.368Improved
add internal pattern extraction to TADP (ablation)WeatherPEFT · Downscaling T2m (limited budget)RMSE: 1.140 -> 1.119Improved
add external pattern integration to TADP (ablation)WeatherPEFT · Downscaling T2m (limited budget)RMSE: 1.130 -> 1.119Improved
add annealed randomness to Fisher-guided selection (ablation)SFAS · Downscaling T2m (limited budget)RMSE: 1.130 -> 1.119Improved
add internal pattern extraction (larger budget) (ablation)WeatherPEFT · Downscaling T2m (increased budget)RMSE: 0.970 -> 0.916Improved
increase selected parameter fraction k from 0.001 to 0.04 (ablation)WeatherPEFT · Regional precipitation 12hSEEPS: 0.368 -> 0.302Improved
increase LoRA rank (8 to 256) at fixed method (ablation)LoRA · Regional precipitation 12hSEEPS: 0.495 (r=8) -> 0.495 (r=256)No clear effect
lengthen soft prompt from P=20 to P=40 or more (ablation)TADP · Regional precipitation 12hSEEPS: 0.368 -> 0.400Hurt
enlarge adapter hidden dims from (8,6,16) to (32,13,512) (ablation)TADP · Regional precipitation 12hSEEPS: 0.368 -> 0.376Hurt
vary initial decay factor gamma (1.0 to 0.2) (ablation)SFAS · Regional precipitation 12hSEEPS: 0.369 -> 0.368No clear effect
use WeatherPEFT instead of LoRA on a different backbonePrithvi-WxC · Regional precipitation 12hSEEPS: 0.647 -> 0.405Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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