no code implementations • 14 Feb 2025 • Bo Ni, Markus J. Buehler
Here, we introduce VibeGen, a generative AI framework that enables end-to-end de novo protein design conditioned on normal mode vibrations.
1 code implementation • 14 Jan 2025 • Markus J. Buehler
The pursuit of automated scientific discovery has fueled progress from symbolic logic to modern AI, forging new frontiers in reasoning and pattern recognition.
1 code implementation • 4 Jan 2025 • Markus J. Buehler
We present an approach to modifying Transformer architectures by integrating graph-aware relational reasoning into the attention mechanism, merging concepts from graph neural networks and language modeling.
1 code implementation • 8 Nov 2024 • Zhenze Yang, Sarah K. Yorke, Tuomas P. J. Knowles, Markus J. Buehler
Peptides are ubiquitous and important biologically derived molecules, that have been found to self-assemble to form a wide array of structures.
no code implementations • 17 Oct 2024 • Alireza Ghafarollahi, Markus J. Buehler
A set of LLM-driven AI agents collaborate to automate the exploration of the vast design space of MPEAs, guided by predictions from the GNN.
1 code implementation • 16 Oct 2024 • Markus J. Buehler
We propose a recursive learning approach that engages the model in multi-step reasoning, revisiting, and refining intermediate steps before producing a final output in training and inference phases.
2 code implementations • 9 Sep 2024 • Alireza Ghafarollahi, Markus J. Buehler
A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data.
7 code implementations • 5 Sep 2024 • Wei Lu, Rachel K. Luu, Markus J. Buehler
The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities.
1 code implementation • 3 Sep 2024 • Jaime A. Berkovich, Markus J. Buehler
Conway's Game of Life (Life), a well known algorithm within the broader class of cellular automata (CA), exhibits complex emergent dynamics, with extreme sensitivity to initial conditions.
no code implementations • 13 Jul 2024 • Alireza Ghafarollahi, Markus J. Buehler
The design of alloys is a multi-scale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a process that is typically reserved for human experts.
no code implementations • 9 Jul 2024 • Haiqian Yang, Anh Q. Nguyen, Dapeng Bi, Markus J. Buehler, Ming Guo
We demonstrate that multicellular data can be represented with both granular and foam-like physical pictures through a unified graph data structure, considering both cellular interactions and cell junction networks.
3 code implementations • 29 May 2024 • Markus J. Buehler
We present Cephalo, a series of multimodal vision large language models (V-LLMs) designed for materials science applications, integrating visual and linguistic data for enhanced understanding.
1 code implementation • 18 Mar 2024 • Markus J. Buehler
Leveraging generative Artificial Intelligence (AI), we have transformed a dataset comprising 1, 000 scientific papers into an ontological knowledge graph.
3 code implementations • 11 Feb 2024 • Eric L. Buehler, Markus J. Buehler
Starting with a set of pre-trained LoRA adapters, our gating strategy uses the hidden states to dynamically mix adapted layers, allowing the resulting X-LoRA model to draw upon different capabilities and create never-before-used deep layer-wise combinations to solve tasks.
1 code implementation • 22 Jan 2024 • Haiqian Yang, Florian Meyer, Shaoxun Huang, Liu Yang, Cristiana Lungu, Monilola A. Olayioye, Markus J. Buehler, Ming Guo
Multicellular self-assembly into functional structures is a dynamic process that is critical in the development and diseases, including embryo development, organ formation, tumor invasion, and others.
1 code implementation • 14 Nov 2023 • Bo Ni, Markus J. Buehler
Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus far mainly been reserved for humans.
no code implementations • 30 Oct 2023 • Markus J. Buehler
Here we explore the use of large language models (LLMs) as a tool that can support engineering analysis of materials, applied to retrieving key information about subject areas, developing research hypotheses, discovery of mechanistic relationships across disparate areas of knowledge, and writing and executing simulation codes for active knowledge generation based on physical ground truths.
no code implementations • 16 Oct 2023 • Markus J. Buehler
The resulting MechGPT LLM foundation model is used in a series of computational experiments to explore its capacity for knowledge retrieval, various language tasks, hypothesis generation, and connecting knowledge across disparate areas.
no code implementations • 16 Oct 2023 • Bo Ni, David L. Kaplan, Markus J. Buehler
Through evolution, nature has presented a set of remarkable protein materials, including elastins, silks, keratins and collagens with superior mechanical performances that play crucial roles in mechanobiology.
no code implementations • 15 Sep 2023 • Rachel K. Luu, Markus J. Buehler
The model has proven that it is able to accurately recall information about biological materials and is further enhanced with enhanced reasoning ability, as well as with retrieval-augmented generation to incorporate new data during generation that can also help to traceback sources, update the knowledge base, and connect knowledge domains.
1 code implementation • 7 May 2023 • Markus J. Buehler
In a broader sense, this work illustrates a form of multiscale modeling that relates a set of ultimate building blocks (here, byte-level utf8 characters that define the nature of the physical system at hand) to complex output.
no code implementations • 11 Apr 2023 • Wei Lu, Nic A. Lee, Markus J. Buehler
Spider webs are incredible biological structures, comprising thin but strong silk filament and arranged into complex hierarchical architectures with striking mechanical properties (e. g., lightweight but high strength, achieving diverse mechanical responses).
no code implementations • 14 Jan 2023 • Markus J. Buehler
Learning from nature has been a quest of humanity for millennia.
no code implementations • 7 Sep 2020 • Mario Milazzo, Gang Seob Jung, Serena Danti, Markus J. Buehler
Using a one-dimensional string model as a model system, we investigate the roles of hydration and load direction on wave propagation along the collagen peptide and the related energy dissipation.
Applied Physics