AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

BLIPs: Bayesian Learned Interatomic Potentials

Dario Coscia, Pim De Haan, Max Welling

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian decision-making under uncertainty · 0 citations (OpenAlex)

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 BLIP variational adaptive dropoutGNN · N-bodyMSE x1e-1: 0.121 -> 0.092Improved
add BLIP variational adaptive dropoutEGNN · N-bodyMSE x1e-1: 0.069 -> 0.060Hurt
use BLIP instead of MC Dropout (p=0.5)EGNN · N-bodyNLL: 0.91 -> -12.52Improved
use Deep Ensemble instead of BLIPEGNN · N-bodyNLL: -12.52 -> -16.22Improved
use BLIP instead of Deep EnsemblePaiNN · Ammonia OODforces MAE: 48.03 -> 41.93Improved
use BLIP instead of Deep EnsemblePaiNN · Ammonia OODenergy MAE: 11.71 -> 11.51Improved
fine-tune with BLIP and random structure selectionORB v3 · MATPES PBEenergy MAE: 111.83 -> 96.65Improved
fine-tune with BLIP and random structure selectionORB v3 · MATPES PBEforces MAE: 110.84 -> 105.12Improved
select active-learning structures by BLIP uncertainty instead of randomly (ablation)ORB v3 + BLIP · MATPES PBEenergy MAE: 96.65 -> 91.13Improved
select active-learning structures by BLIP uncertainty instead of randomly (ablation)ORB v3 + BLIP · MATPES PBEforces MAE: 105.12 -> 103.85Improved
use BLIP instead of Deep Ensemble for calibrationORB v3 · SiO2 (1024 samples)ECE: 0.247 -> 0.032Improved
use BLIP instead of Deep Ensemble for variance-error rank correlationORB v3 · SiO2 (1024 samples)Spearman correlation: 0.676 -> 0.602Hurt

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