LAMM: MIT Laboratory for Atomistic and Molecular Mechanics

university

https://meche.mit.edu/people/faculty/mbuehler@mit.edu

AI & ML interests

PI: Markus J. Buehler, MIT. Our research focus on developing a new paradigm that designs materials from the molecular scale, using MD, ML and other methods.

Recent Activity

mjbuehler updated a dataset 1 day ago

lamm-mit/gemma4-interpretability

mjbuehler published a dataset 1 day ago

lamm-mit/gemma4-interpretability

mjbuehler updated a dataset 3 days ago

lamm-mit/swarmworld-data

View all activity

Papers

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange

View all Papers

lamm-mit 's papers 5

Submitted by

Markus Buehler

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

LAMM: MIT Laboratory for Atomistic and Molecular Mechanics

16 2

Submitted by

Markus Buehler

Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange

LAMM: MIT Laboratory for Atomistic and Molecular Mechanics

242 2

Submitted by

Markus Buehler

BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning

LAMM: MIT Laboratory for Atomistic and Molecular Mechanics

1 2

Submitted by

Markus Buehler

GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design

LAMM: MIT Laboratory for Atomistic and Molecular Mechanics

Submitted by

Markus Buehler

Selective Imperfection as a Generative Framework for Analysis, Creativity and Discovery

LAMM: MIT Laboratory for Atomistic and Molecular Mechanics

5 3

AI & ML interests

Recent Activity

Papers

Team members 1

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange

BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning

GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design

Selective Imperfection as a Generative Framework for Analysis, Creativity and Discovery