https://github.com/CederGroupHub/chgnet
공식 코드CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling
Papers with Code 아카이브
Atomic Forces
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Predicion of the atomic forces, generally calculated with a quantum mechanical code (e.g. at DFT theory).
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/divelab/AIRS
공식 코드QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
https://github.com/intellabs/matsciml
공식 코드MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
https://github.com/mir-group/allegro
공식 코드Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
https://github.com/tongzhugroup/mddatasetbuilder
공식 코드Neural Network Based in Silico Simulation of Combustion Reactions
https://gitlab.com/hylleraasplatform/hyal
공식 코드Learning atomic forces from uncertainty-calibrated adversarial attacks
https://gitlab.com/zaverkin_v/gmnn
공식 코드Transfer learning for chemically accurate interatomic neural network potentials
https://github.com/mir-group/pair_allegro
Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
https://github.com/teddykoker/e3nn.c
Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
https://github.com/wengong-jin/abdockgen
Antibody-Antigen Docking and Design via Hierarchical Equivariant Refinement
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.