AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Sparsity-promoting Fine-tuning for Equivariant Materials Foundation Model

Youngwoo Cho, Seunghoon Yi, Wooil Yang, Sungmo Kang, Young-Woo Son, Jaegul Choo, Joonseok Lee, Soo Kyung Kim, Hongkee Yoon

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
use sparsity-promoting fine-tuning (L) instead of full fine-tuning on LAM Sn energyMACE-MP-0b3 · LAM Snenergy MAE (meV/atom): 32.74 -> 2.18Improved
use sparse adaptation instead of ELoRA low-rank adaptation on TM-O-Spin forcesMACE-MP-0b3 with spin layers · TM-O-Spinforce MAE (meV/A): 116.31 -> 70.46Improved
use sparse adaptation (L) instead of full fine-tuning on TM-O-Spin energyMACE-MP-0b3 with spin layers · TM-O-Spinenergy MAE (meV/atom): 11.58 -> 9.50Improved
use sparse adaptation (L) instead of ELoRA on rMD17 Aspirin forcesMACE-OFF23 · rMD17 Aspirinforce MAE (meV/A): 8.52 -> 7.56Improved
switch from low sparsity (lambda_tau 0.01) to high sparsity (0.3) on rMD17 Aspirin forces (ablation)sparse fine-tuning · rMD17 Aspirinforce MAE (meV/A): 7.56 -> 8.22Hurt
update only the FCTP layers instead of the linear layers (ablation)sparse fine-tuning · Ti (LAM)energy and force MAEHurt
update both linear and FCTP layers (All) instead of linear only (ablation)sparse fine-tuning · Ti (LAM)energy and force MAENo clear effect
use Linear-only vs All updates, comparing module sparsity growth with lambda_tau (ablation)sparse fine-tuning · Ti (LAM)layer-wise sparsityMixed
use high-sparsity setting (lambda_tau 0.3) vs low on TM-O-Spin energy (ablation)sparse fine-tuning · TM-O-Spinenergy MAE (meV/atom): 9.50 -> 10.57Hurt
use sparse fine-tuning instead of full fine-tuning on large MP-mag dataset forcesMACE-MP-0b3 with spin layers · MP-magforce MAE (meV/A): 37.56 -> 42.11Hurt
use sparse All (lambda_tau 0.05) instead of full fine-tuning on MP-mag energyMACE-MP-0b3 with spin layers · MP-magenergy MAE (meV/atom): 18.75 -> 16.56Improved
fine-tune with sparse method on NequIP-OAM-L instead of full fine-tuning (Aspirin energy)NequIP-OAM-L · rMD17 Aspirinenergy MAE: 0.37 -> 0.33Improved

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