JanusPipe introduces SymFold and WaveK to enable efficient 3D-parallel training for conservative MLIPs, reporting 1.51x and 1.45x average throughput gains over 1F1B and Hanayo baselines on 32 GPUs.
hub Mixed citations
Levine, Muhammed Shuaibi, Evan Walter Clark Spotte-Smith, Michael G
Mixed citation behavior. Most common role is background (60%).
21
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 4
dataset 1
citation-polarity summary
representative citing papers
QT-Net predicts atomic electron populations and multipoles via a new SOAP-cluster held-out test, improving molecular property prediction and recovering QM9 dipole moments from per-atom outputs.
Kernels from pretrained MLIP latent spaces outperform standard acquisition methods in active learning for reactive chemistry, reducing required labels by 38% for energy error and 28% for force error.
Surrogate functionals for OF-DFT are defined and trained solely to make fixed density optimization reach the ground-state density, achieving competitive accuracy on QM9 and QMugs without O(N^3) orthonormalization.
A closed-loop framework jointly optimizes molecular composition and geometry in multi-component systems, demonstrated by a 30% reduction in activation barrier for a Claisen rearrangement via post-hoc validation.
OmniMol transfers a billion-jet pre-trained PET foundation model from HEP to molecular dynamics via an interaction-matrix attention bias, delivering strong performance on the oMol dataset with minimal fine-tuning and fast inference.
Force-aware Neural Tangent Kernels combined with chunked acquisition provide scalable and distribution-robust active learning for MLIPs, outperforming baselines on OC20 and remaining competitive on other benchmarks.
Structural pruning of SO(3) equivariant atomistic models from large checkpoints yields 1.5-4x fewer parameters and 2.5-4x less pre-training compute than small models trained from scratch, while outperforming them on most Matbench Discovery metrics and downstream tasks.
Suiren-1.0 is a family of three molecular foundation models (Base, Dimer, ConfAvg) pre-trained on 70M+ DFT samples and distilled to achieve claimed state-of-the-art performance on quantum property prediction tasks from 2D inputs.
UBio-MolFM achieves ab initio-level fidelity on large out-of-distribution biomolecular systems using a new multi-fidelity dataset, E2Former-V2 architecture, and three-stage curriculum learning.
Atompack delivers 96x faster shuffled reads and 79% smaller artifacts than ASE LMDB baselines for complete-record atomistic ML training workloads.
Universal MLIPs serve as configuration generators whose DFT-relabeled subsamples enable one-shot or iterative training of material-specific MLIPs that recover accurate reactive energy profiles with 600-2000 DFT calculations.
CSP-MACE-Å matches PBE DFT with Neumann-Perrin and B86bPBE-XDM DFT performance on two CSP benchmark sets while running much faster and benefiting from harmonic free-energy reranking.
Spatial statistics on voxelized structures using FFT correlations and PCA yield low-dimensional convex features that support accurate predictions with as few as 10 training samples.
Fine-tuned MACE MLIPs achieve lower mean absolute errors on catalytic reaction energies and barriers than from-scratch models, with a large fine-tuned model performing best on both metallic and oxide systems including out-of-distribution cases.
El Agente Estructural is a new multimodal agent that performs natural-language-driven 3D molecular geometry editing and generation using integrated domain tools and vision-language models.
Benchmarks of 15 MLIPs show parameter count and training set size correlate with accuracy, architecture drives speed and memory, and explicit Coulomb terms provide no benefit.
Different uMLIPs encode chemical space in distinct ways, with high cross-model feature reconstruction errors, and fine-tuning preserves strong pre-training bias in the latent features.
A review of classical and AI-assisted methods for modeling chemical disorder in atomistic simulations of alloys and complex materials.
Machine learning models trained on quantum mechanical data can predict defect properties in solids with high accuracy but at much lower computational cost than traditional methods.
A review of generative AI for inverse design of inorganic compounds, analyzing adaptations for their complexity in composition, geometry, symmetry, and electronic structure, with discussion of future benchmarks and synthesizability metrics.
citing papers explorer
-
QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
QT-Net predicts atomic electron populations and multipoles via a new SOAP-cluster held-out test, improving molecular property prediction and recovering QM9 dipole moments from per-atom outputs.
-
Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs
Kernels from pretrained MLIP latent spaces outperform standard acquisition methods in active learning for reactive chemistry, reducing required labels by 38% for energy error and 28% for force error.
-
Surrogate Functionals for Machine-Learned Orbital-Free Density Functional Theory
Surrogate functionals for OF-DFT are defined and trained solely to make fixed density optimization reach the ground-state density, achieving competitive accuracy on QM9 and QMugs without O(N^3) orthonormalization.
-
Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
Force-aware Neural Tangent Kernels combined with chunked acquisition provide scalable and distribution-robust active learning for MLIPs, outperforming baselines on OC20 and remaining competitive on other benchmarks.
-
Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
Structural pruning of SO(3) equivariant atomistic models from large checkpoints yields 1.5-4x fewer parameters and 2.5-4x less pre-training compute than small models trained from scratch, while outperforming them on most Matbench Discovery metrics and downstream tasks.
-
Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets
Atompack delivers 96x faster shuffled reads and 79% smaller artifacts than ASE LMDB baselines for complete-record atomistic ML training workloads.