Pith. sign in

REVIEW 5 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

Duo Zhang , Xinzijian Liu , Xiangyu Zhang , Chengqian Zhang , Chun Cai , Hangrui Bi , Yiming Du , Xuejian Qin
show 35 more authors
Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M. York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang
This is my paper · ORCID
classification physics.chem-phcond-mat.mtrl-sciphysics.comp-ph
keywords atomicdpa-2modelacrossapproachdownstreamlamslarge
verification ladder T0 review T1 audit T2 compute T3 formal
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). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

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

    physics.comp-ph 2026-07 accept novelty 6.0 of 10

    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.

  2. Multi-task parallelism for robust pre-training of graph foundation models on multi-source, multi-fidelity atomistic modeling data

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A method that distributes per-dataset decoding heads across GPUs enables pre-training of a multi-task graph neural network on 24 million atomistic structures from five datasets.

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

    cs.CE 2026-06 unverdicted novelty 5.0 of 10

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

  4. A Study on the Fine-Tuning Performance of Universal Machine-Learned Interatomic Potentials (U-MLIPs)

    physics.comp-ph 2025-06 conditional novelty 4.0 of 10

    Fine-tuning universal MACE potentials on targeted datasets generally improves accuracy and convergence speed, though data selection, not the foundation model alone, determines success.

  5. HPC-AI Coupling Methodology for Scientific Applications

    cs.CE 2025-06 conditional novelty 3.0 of 10

    A methodology that organizes HPC-AI integration into surrogate, directive, and coordinate patterns is demonstrated on materials science applications.

Pith tools