Pith. sign in

REVIEW 7 cited by

DPA-2: a large atomic model as a multi-task learner

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.15492 v2 pith:BNUB47MQ submitted 2023-12-24 physics.chem-ph cond-mat.mtrl-sciphysics.comp-ph

DPA-2: a large atomic model as a multi-task learner

classification physics.chem-ph cond-mat.mtrl-sciphysics.comp-ph
keywords atomicdpa-2modelacrossapproachdownstreamlamslarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning

    cs.LG 2026-02 unverdicted novelty 7.0

    GraphVec produces transferable fixed-dimensional graph embeddings via spectral features from multi-scale global graphs and a convergent mean-alignment procedure, outperforming baselines on cross-domain few-shot classi...

  2. dpti: An Automated Thermodynamic Integration Workflow for Phase Diagram Calculations with Machine Learning Interatomic Potentials

    physics.comp-ph 2026-07 accept novelty 6.0

    dpti automates reversible HTI/TTI/pTI and Gibbs-Duhem workflows that connect analytic reference free energies to MLIP solids and liquids and produce phase boundaries with error estimates.

  3. Siamese Foundation Models for Crystal Structure Prediction

    cond-mat.mtrl-sci 2025-03 unverdicted novelty 6.0

    DAO pretrains Siamese diffusion-based models on stable/unstable crystal data to achieve 100% experimental match on Cr6Os2 and 2000x speedup over DFT on real superconductors.

  4. MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures

    cond-mat.mtrl-sci 2024-05 unverdicted novelty 6.0

    MatterSim delivers a single deep learning force field that simulates inorganic materials across elements, 0-5000 K, and up to 1000 GPa with near first-principles accuracy for lattice dynamics, mechanics, and Gibbs fre...

  5. Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery

    cs.CE 2026-06 conditional novelty 5.0

    An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.

  6. ASTEROID: A Spatiotemporal Information Transformer for Forecasting Multi-Step Time Series of Molecular Dynamics

    cs.LG 2026-06 unverdicted novelty 5.0

    ASTEROID is a spatiotemporal Transformer that predicts multi-step MD atomic coordinates with claimed higher accuracy and lower cost than iterative simulation on quantum-derived datasets.

  7. Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery

    cs.CE 2026-06 unverdicted novelty 3.0

    Introduces a scalable AI skill framework for autonomous microkinetics discovery that automates workflows and evaluates surrogate reliability.