pith. sign in

arxiv: 2312.15492 · v2 · pith:BNUB47MQnew · submitted 2023-12-24 · ⚛️ physics.chem-ph · cond-mat.mtrl-sci· physics.comp-ph

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

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
classification ⚛️ physics.chem-ph cond-mat.mtrl-sciphysics.comp-ph
keywords atomicdpa-2modelacrossapproachdownstreamlamslarge
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 4 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. 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.

  3. 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...

  4. 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.