AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Machine Learning Hamiltonians are Accurate Energy-Force Predictors

Seongsu Kim, Chanhui Lee, Yoonho Kim, Seongjun Yun, Honghui Kim, Nayoung Kim, Changyoung Park, Sehui Han, Sungbin Lim, Sungsoo Ahn

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 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
replace QHFlow with QHFlow2 (SO(2) eSEN backbone plus two-stage pair update)QHFlow · QH9-stable-idHamiltonian MAE (uHa): 23.0 -> 9.2 (QHFlow2-m, 43M)Improved
replace QHFlow with QHFlow2 on downstream energyQHFlow · QH9-stable-idtotal energy MAE (meV): 2.37 -> 0.69 (QHFlow2-m)Improved
scale QHFlow2 from 12M to 990M parameters (ablation)QHFlow2 · QH9-stable-idHamiltonian MAE (uHa): 16.3 -> 4.6Improved
scale QHFlow2 from 12M to 990M parameters (ablation)QHFlow2 · QH9-stable-idforce MAE (meV/A): 3.1 -> 1.2 (non-monotonic: 2.1, 1.4 in between)Mixed
increase training set size (ablation)QHFlow2-m · MD benchmark (salicylic acid, aspirin)Hamiltonian, orbital, energy and force MAEImproved
use QHFlow2 Hamiltonian predictor instead of MLIP baselinesNequIP · MD17/rMD17 (six molecules)energy MAE: up to 20x lower energy MAEImproved
use QHFlow2 Hamiltonian predictor instead of NequIPNequIP · MD17/rMD17 (six molecules)force MAENo clear effect
add SO(3) tensor-product refinement as second stage of pair update (ablation)QHFlow2 · off-diagonal Hamiltonian blocks, cutoff/radial-basis sensitivityHamiltonian off-diagonal accuracyImproved
initialize SCF with predicted Hamiltonian instead of MinAODFT SCF · QH9-stable-iid test (300 molecules)SCF cycles ratio: QHFlow2-l 2.18x end-to-end speedupImproved
scale QHNet beyond about 40M parameters (ablation)QHNet · QH9training stabilityHurt

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