Markus J. Buehler
YOU?
Author Swipe
View article: Frontiers of biological material intelligence
Frontiers of biological material intelligence Open
Biological materials exhibit a form of intelligence that enables them to sense, adapt, and self-optimize in response to their environments. Unlike synthetic materials, which are often designed for singular, static functions, natural materi…
View article: Rapid and automated alloy design with graph neural network-powered large language model-driven multi-agent AI
Rapid and automated alloy design with graph neural network-powered large language model-driven multi-agent AI Open
A multi-agent artificial intelligence (AI) model is developed to automate the discovery of new metallic alloys, integrating multimodal data and external knowledge, including insights from physics via atomistic simulations. The system consi…
View article: An open-source and low-cost dual-extruder 3D printer for macroscale biotic materials
An open-source and low-cost dual-extruder 3D printer for macroscale biotic materials Open
This work presents the design and fabrication of a novel, dual-extruder biotic 3D printer, tailored for precise deposition of natural biomaterials such as pectin, chitosan, and cellulose. Moving beyond the limitations of traditional thermo…
View article: An Open-Source and Low-Cost Dual Extruder 3D Printer for Macroscale Biotic Materials
An Open-Source and Low-Cost Dual Extruder 3D Printer for Macroscale Biotic Materials Open
This work presents the design and fabrication of a novel, dual-extruder biotic 3D printer tailored for precise deposition of natural biomaterials such as pectin, chitosan, and cellulose. Moving beyond the limitations of traditional thermop…
View article: MusicSwarm: Biologically Inspired Intelligence for Music Composition
MusicSwarm: Biologically Inspired Intelligence for Music Composition Open
We show that coherent, long-form musical composition can emerge from a decentralized swarm of identical, frozen foundation models that coordinate via stigmergic, peer-to-peer signals, without any weight updates. We compare a centralized mu…
View article: Generative Artificial Intelligence Extracts Structure-Function Relationships from Plants for New Materials
Generative Artificial Intelligence Extracts Structure-Function Relationships from Plants for New Materials Open
Large language models (LLMs) have reshaped the research landscape by enabling new approaches to knowledge retrieval and creative ideation. Yet their application in discipline-specific experimental science, particularly in highly multi-disc…
View article: Agentic deep graph reasoning yields self-organizing knowledge networks
Agentic deep graph reasoning yields self-organizing knowledge networks Open
We present an agentic, autonomous graph expansion framework that iteratively structures and refines knowledge in situ. Unlike conventional knowledge graph construction methods relying on static extraction or single-pass learning, our appro…
View article: In Situ Graph Reasoning and Knowledge Expansion Using Graph‐PRefLexOR
In Situ Graph Reasoning and Knowledge Expansion Using Graph‐PRefLexOR Open
The pursuit of automated scientific discovery has evolved from symbolic logic to modern AI, advancing reasoning and pattern recognition. While large language models (LLMs) excel in fluency and recall, they often struggle with structured re…
View article: De novo design of peptides localizing at the interface of biomolecular condensates
De novo design of peptides localizing at the interface of biomolecular condensates Open
The interface of biomolecular condensates has been shown to play an important role in processes such as protein aggregation and biochemical reactions. Targeted modulation of these interfaces could, therefore, serve as an effective strategy…
View article: Graph-aware isomorphic attention for adaptive dynamics in transformers
Graph-aware isomorphic attention for adaptive dynamics in transformers Open
We present an approach for modifying transformer architectures by integrating graph-aware relational reasoning into the attention mechanism, merging concepts from graph neural networks and language modeling. Building on the inherent connec…
View article: Enhanced Electrochemical Properties of Biobased Activated Carbon for Supercapacitors
Enhanced Electrochemical Properties of Biobased Activated Carbon for Supercapacitors Open
Supercapacitors are great candidates for energy boosting, power, and memory backup. However, they suffer from low‐energy density, relatively high cost, and carbon footprint problems due to their electrode materials, such as commonly used a…
View article: Fine-tuning large language models for domain adaptation: exploration of training strategies, scaling, model merging and synergistic capabilities
Fine-tuning large language models for domain adaptation: exploration of training strategies, scaling, model merging and synergistic capabilities Open
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. In …
View article: Learning the rules of peptide self-assembly through data mining with large language models
Learning the rules of peptide self-assembly through data mining with large language models Open
Peptides are ubiquitous and important biomolecules that self-assemble into diverse structures. Although extensive research has explored the effects of chemical composition and exterior conditions on self-assembly, a systematic study consol…
View article: Sewage sludge hydrochar characterization and valorization via hydrothermal processing for 3D printing
Sewage sludge hydrochar characterization and valorization via hydrothermal processing for 3D printing Open
Sewage sludge, a biosolid product of wastewater processing, is an often-overlooked source of rich organic waste. Hydrothermal processing has shown promise in converting sewage sludge into valorized materials with potential application in b…
View article: Discovery of mammalian collagens I and III within ancient poriferan biopolymer spongin
Discovery of mammalian collagens I and III within ancient poriferan biopolymer spongin Open
Spongin is a fundamental biopolymer that has played a crucial role in the skeletogenesis of keratosan sponges for over 800 million years. This biomaterial had so far remained chemically unidentified and believed to be an enigmatic type of …
View article: Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks
Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks Open
We present an agentic, autonomous graph expansion framework that iteratively structures and refines knowledge in situ. Unlike conventional knowledge graph construction methods relying on static extraction or single-pass learning, our appro…
View article: Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model
Agentic End-to-End De Novo Protein Design for Tailored Dynamics Using a Language Diffusion Model Open
Proteins are dynamic molecular machines whose biological functions, spanning enzymatic catalysis, signal transduction, and structural adaptation, are intrinsically linked to their motions. Designing proteins with targeted dynamic propertie…
View article: Automating alloy design and discovery with physics-aware multimodal multiagent AI
Automating alloy design and discovery with physics-aware multimodal multiagent AI Open
The design of new alloys is a multiscale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a proc…
View article: Revealing Diatom‐Inspired Materials Multifunctionality
Revealing Diatom‐Inspired Materials Multifunctionality Open
Diatoms have been described as “nanometer‐born lithographers” because of their ability to create sophisticated 3D amorphous silica exoskeletons. The hierarchical architecture of these structures provides diatoms with mechanical protection …
View article: In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR
In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR Open
The pursuit of automated scientific discovery has fueled progress from symbolic logic to modern AI, forging new frontiers in reasoning and pattern recognition. Transformers function as potential systems, where every possible relationship r…
View article: Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers
Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers Open
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. Building on the inherent connect…
View article: Revealing diatom-inspired materials multifunctionality
Revealing diatom-inspired materials multifunctionality Open
Diatoms have been described as nanometer-born lithographers because of their ability to create sophisticated three-dimensional amorphous silica exoskeletons. The hierarchical architecture of these structures provides diatoms with mechanica…
View article: Generative design and molecular mechanics characterization of silk proteins based on unfolding behavior
Generative design and molecular mechanics characterization of silk proteins based on unfolding behavior Open
A generative design and simulation framework reveals unfolding mechanics of silk-inspired proteins, enabling exploration of sequence–structure–property relationships and offering insights into the mechanobiological basis of fiber performan…
View article: Molecular analysis and design using generative artificial intelligence <i>via</i> multi-agent modeling
Molecular analysis and design using generative artificial intelligence <i>via</i> multi-agent modeling Open
We report the use of a multiagent generative artificial intelligence framework, the X-LoRA-Gemma large language model (LLM), to analyze, design and test molecular design.
View article: SciAgents: Automating Scientific Discovery Through Bioinspired Multi‐Agent Intelligent Graph Reasoning
SciAgents: Automating Scientific Discovery Through Bioinspired Multi‐Agent Intelligent Graph Reasoning Open
A key challenge in artificial intelligence (AI) is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in…