Atomistic Language Models Understand and Generate Materials

• URL: http://arxiv.org/abs/2606.21395v1
• Date: Fri, 19 Jun 2026 13:01:45 GMT
• Title: Atomistic Language Models Understand and Generate Materials
• Abstract summary: We introduce Atomistic Language Models (ALMs) to pursue native multimodality.<n>A single language backbone understands atomistic structures and generates materials from natural language.<n>ALMs achieve state-of-the-art results on crystal structure prediction and de novo generation.
• Score: 4.0674327089133175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Atomistic structure and natural language have long been modeled separately, with language models either calling atomistic models as tools or being fine-tuned on lossy textual encodings that discard atomistic information. We introduce Atomistic Language Models (ALMs) to pursue native multimodality, in which a single language backbone understands atomistic structures, generates materials from natural language, and optimizes crystal structures as instructed by text. By unifying a pretrained atomistic encoder, large language model, and denoising diffusion model through purely continuous projectors and staged training, ALMs achieve state-of-the-art results on crystal structure prediction and de novo generation. ALMs are enabled by a continuous bridge that maps language model embeddings directly into the steering space of atomistic diffusion, and are assisted by Text-to-Crystal Feynman-Kac (T2C-FK), a particle-based sampler that scores partial denoising trajectories to enforce stoichiometric targets at inference time. To evaluate the ability of ALMs to optimize and generate materials from natural-language prompts and 3D atom-coordinate inputs, we introduce ALM Bench, the first benchmark for text-conditioned crystal generation and optimization. Code, training data, and model weights will be released soon.

Related papers

• Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language [2.9764168176721992]
  CheMatE is a chemistry-oriented embedding model that jointly captures molecular structure and domain-specific natural language.<n>We train the model using a novel, large-scale corpus of scientific documents that were constructed and curated from FineWeb and ChemPile.<n>This design exposes the model to SMILES-curated scientific literature, enabling bi-semantic understanding.
  arXiv  Detail & Related papers  (2026-08-04T15:57:38Z)
• In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics [109.99871326497333]
  In-Context Model Predictive Generation (ICMPG) is a framework that integrates language-model planning with inference-time physical feedback.<n>ICMPG reformulates motion synthesis as a Model Predictive Control (MPC)-like process with two modules.
  arXiv  Detail & Related papers  (2026-06-25T12:50:33Z)
• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation [25.009649087291432]
  CrysLLMGen is a hybrid framework that integrates an LLM with a diffusion model to leverage their complementary strengths for crystal material generation.<n>Our framework outperforms state-of-the-art generative models across several benchmark tasks and datasets.
  arXiv  Detail & Related papers  (2025-10-27T06:08:19Z)
• Text to Band Gap: Pre-trained Language Models as Encoders for Semiconductor Band Gap Prediction [9.325818199739759]
  We investigate transformer-based language models, including RoBERTa, T5, Llama-3, and MatSciBERT, for predicting band gaps of semiconductor materials.<n>The inputs encode key material features, such as chemical composition, crystal system, space group, and other structural and electronic properties.
  arXiv  Detail & Related papers  (2025-01-07T00:56:26Z)
• L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects [53.4874127399702]
  We propose a language agent with chain-of-3D-thoughts (L3GO), an inference-time approach that can reason about part-based 3D mesh generation. We develop a new benchmark, Unconventionally Feasible Objects (UFO), as well as SimpleBlenv, a wrapper environment built on top of Blender. Our approach surpasses the standard GPT-4 and other language agents for 3D mesh generation on ShapeNet.
  arXiv  Detail & Related papers  (2024-02-14T09:51:05Z)
• Fine-Tuned Language Models Generate Stable Inorganic Materials as Text [53.81190146434045]
  Fine-tuning large language models on text-encoded atomistic data is simple to implement yet reliable.<n>We show that our strongest model can generate materials predicted to be metastable at about twice the rate of CDVAE.<n>Because of text prompting's inherent flexibility, our models can simultaneously be used for unconditional generation of stable material.
  arXiv  Detail & Related papers  (2024-02-06T20:35:28Z)
• On decoder-only architecture for speech-to-text and large language model integration [59.49886892602309]
  Speech-LLaMA is a novel approach that effectively incorporates acoustic information into text-based large language models. We conduct experiments on multilingual speech-to-text translation tasks and demonstrate a significant improvement over strong baselines.
  arXiv  Detail & Related papers  (2023-07-08T06:47:58Z)
• Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials [4.813020904720316]
  BLMM Crystal Transformer is a neural network based probabilistic generative model for generative and tinkering design of inorganic materials. It can generate chemically valid materials compositions with as high as 89.7% charge neutrality and 84.8% balanced electronegativity. A user-friendly web app has been developed for computational materials doping and can be accessed freely at urlwww.materialsatlas.org/blmtinker.
  arXiv  Detail & Related papers  (2022-04-25T20:20:26Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.