paper-with-me

Papers

Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials

2022-04-25 · Lai Wei, Qinyang Li, Yuqi Song, Stanislav Stefanov, Edirisuriya M. D. Siriwardane, Fanglin Chen, Jianjun Hu

Self-supervised neural language models have recently achieved unprecedented success, from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior performance in the generation, structure classification, and functional predictions for proteins and molecules with learned representations. However, most of the masking-based pre-trained language models are not designed for generative design, and their black-box nature makes it difficult to interpret their design logic. Here we propose BLMM Crystal Transformer, a neural network based probabilistic generative model for generative and tinkering design of inorganic materials. Our model is built on the blank filling language model for text generation and has demonstrated unique advantages in learning the "materials grammars" together with high-quality generation, interpretability, and data efficiency. It can generate chemically valid materials compositions with as high as 89.7\% charge neutrality and 84.8\% balanced electronegativity, which are more than 4 and 8 times higher compared to a pseudo random sampling baseline. The probabilistic generation process of BLMM allows it to recommend tinkering operations based on learned materials chemistry and makes it useful for materials doping. Combined with the TCSP crysal structure prediction algorithm, We have applied our model to discover a set of new materials as validated using DFT calculations. Our work thus brings the unsupervised transformer language models based generative artificial intelligence to inorganic materials. A user-friendly web app has been developed for computational materials doping and can be accessed freely at \url{www.materialsatlas.org/blmtinker}.

📄 PDF Abstract BibTeX arXiv:2204.11953

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSelf-LearningText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Probabilistic Generative Transformer Language models for Generative Design of Molecules

2022-09-20 · Lai Wei, Nihang Fu, Yuqi Song, Qian Wang 외

Self-supervised neural language models have recently found wide applications in generative design of organic molecules and protein sequences as well as representation learning for downstream structure classification and …

Language ModelingLanguage ModellingRepresentation Learning

CrystalFormer-RL: Reinforcement Fine-Tuning for Materials Design

2025-04-03 · Zhendong Cao, Lei Wang

Reinforcement fine-tuning has instrumental enhanced the instruction-following and reasoning abilities of large language models. In this work, we explore the applications of reinforcement fine-tuning to the autoregressive…

Band GapDielectric ConstantInstruction Followingmultimodal generation+2

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

2026-04-02 · Tin Hadži Veljković, Joshua Rosenthal, Ivor Lončarić, Jan-Willem van de Meent arxiv

Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are costly to train and slow to sample. We present Crystalite, a lightweight diffusi…

Transformer-Enhanced Variational Autoencoder for Crystal Structure Prediction

2025-02-13 · Ziyi Chen, Yang Yuan, Siming Zheng, Jialong Guo 외

Crystal structure forms the foundation for understanding the physical and chemical properties of materials. Generative models have emerged as a new paradigm in crystal structure prediction(CSP), however, accurately captu…

Prediction

Understanding Ice Crystal Habit Diversity with Self-Supervised Learning

2025-09-09 · Joseph Ko, Hariprasath Govindarajan, Fredrik Lindsten, Vanessa Przybylo 외 arxiv

Ice-containing clouds strongly impact climate, but they are hard to model due to ice crystal habit (i.e., shape) diversity. We use self-supervised learning (SSL) to learn latent representations of crystals from ice cryst…

Self-Supervised Learning