Di He

Di He

Auto-generated profile, based on publicly available information

Di He

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
ZHZhenyu He
Zhenyu He
ZZZexuan Zhong
Zexuan Zhong
TCTianle Cai
Tianle Cai
JLJason Lee
Jason Lee
DHDi He
Di He
Zhenyu He, Zexuan Zhong, Tianle Cai, Jason Lee, Di He. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

19 August 2024 in Nature Communications
Verified
Journal Article
Open access
PDF file
SLShuqi Lu
Shuqi Lu
ZGZhifeng Gao
Zhifeng Gao
DHDi He
Di He
LZLinfeng Zhang
Linfeng Zhang
GKGuolin Ke
Guolin Ke
Quantum chemical (QC) property prediction is crucial for computational materials and drug design, but relies on expensive electronic structure calculations like density functional theory (DFT). Recent deep learning methods accelerate this process using 1D SMILES or 2D graphs as inputs but struggle to achieve high accuracy as most QC properties depend on refined 3D molecular equilibrium conformations. We introduce , a deep learning approach that leverages 3D conformations for accurate QC property prediction. first generates a raw 3D conformation using RDKit then iteratively refines it towards DFT equilibrium conformation using neural networks, which is finally used to predict the QC properties. To effectively learn this conformation update process, we introduce a two-track Transformer model backbone and a novel training approach. Our benchmarking results demonstrate that the proposed significantly improves the accuracy of QC property prediction in various datasets.

13 February 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
RLRuichen Li
Ruichen Li
HYHaotian Ye
Haotian Ye
DJDu Jiang
Du Jiang
XWXuelan Wen
Xuelan Wen
CWChuwei Wang
Chuwei Wang
LWLiwei Wang
Liwei Wang

1 January 2025
Verified
Conference Paper
Open access
PDF file
GFGuhao Feng
Guhao Feng
KYKai Yang
Kai Yang
YGYuntian Gu
Yuntian Gu
XAXinyue Ai
Xinyue Ai
SLShengjie Luo
Shengjie Luo
LWLiwei Wang
Liwei Wang
Guhao Feng, Kai Yang, Yuntian Gu, Xinyue Ai, Shengjie Luo, Jiacheng Sun, Di He, Zhenguo Li, Liwei Wang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

22 June 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
YGYuntian Gu
Yuntian Gu
WLWenrui Li
Wenrui Li
HLHeng Lin
Heng Lin
BZBo Zhan
Bo Zhan
RLRuichen Li
Ruichen Li
DLDingshun Lv
Dingshun Lv
The rapid development of neural quantum states (NQS) has established it as a promising framework for studying quantum many-body systems. In this work, by leveraging the transformer-based architectures and developing efficient optimization algorithms, we achieve the state-of-the-art results for the doped two-dimensional (2D) Hubbard model, arguably the minimum model for high-Tc superconductivity. Interestingly, we find different attention heads in the NQS ansatz can directly encode correlations at different scales, making it capable of capturing long-range correlations in strongly correlated systems. With these advances, we find evidence for the half-filled stripe in the ground state of 2D Hubbard model with the next nearest neighboring hopping, consistent with experimental observations in cuprates. Our work establishes NQS as a powerful tool for solving challenging many-fermions systems.

28 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
SLShengjie Luo
Shengjie Luo
TCTianlang Chen
Tianlang Chen
YXYixian Xu
Yixian Xu
SZShuxin Zheng
Shuxin Zheng
TLTie-Yan Liu
Tie-Yan Liu
DHDi He
Di He
Unlike vision and language data which usually has a unique format, molecules can naturally be characterized using different chemical formulations. One can view a molecule as a 2D graph or define it as a collection of atoms located in a 3D space. For molecular representation learning, most previous works designed neural networks only for a particular data format, making the learned models likely to fail for other data formats. We believe a general-purpose neural network model for chemistry should be able to handle molecular tasks across data modalities. To achieve this goal, in this work, we develop a novel Transformer-based Molecular model called Transformer-M, which can take molecular data of 2D or 3D formats as input and generate meaningful semantic representations. Using the standard Transformer as the backbone architecture, Transformer-M develops two separated channels to encode 2D and 3D structural information and incorporate them with the atom features in the network modules. When the input data is in a particular format, the corresponding channel will be activated, and the other will be disabled. By training on 2D and 3D molecular data with properly designed supervised signals, Transformer-M automatically learns to leverage knowledge from different data modalities and correctly capture the representations. We conducted extensive experiments for Transformer-M. All empirical results show that Transformer-M can simultaneously achieve strong performance on 2D and 3D tasks, suggesting its broad applicability. The code and models will be made publicly available at https://github.com/lsj2408/Transformer-M.