๐๐ฒ๐บ๐ผ๐ป๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป ๐๐ถ๐ฑ๐ฒ๐ผ: youtu.be/a85-im6ldyQ
๐ฆ๐ผ๐๐ฟ๐ฐ๐ฒ ๐ฐ๐ผ๐ฑ๐ฒ: github.com/blaiszik/mic...
๐๐-๐ฝ๐ผ๐๐ฒ๐ฟ๐ฒ๐ฑ ๐ฑ๐ผ๐ฐ๐๐บ๐ฒ๐ป๐๐ฎ๐๐ถ๐ผ๐ป: deepwiki.com/blaiszik/mic...
ยต๐๐ญ๐๐๐ค interactive CLI
๐คโก๐ฅ๏ธ From ๐๐๐-๐ฅ๐ค๐ฌ๐๐ง๐๐ ๐จ๐ฉ๐ง๐ช๐๐ฉ๐ช๐ง๐ ๐๐๐ฃ๐๐ง๐๐ฉ๐๐ค๐ฃ ๐ฉ๐๐ง๐ค๐ช๐๐ ๐๐-๐๐๐จ๐๐ ๐ง๐๐ก๐๐ญ๐๐ฉ๐๐ค๐ฃ ๐ฉ๐ค ๐๐๐๐-๐๐๐๐๐ก๐๐ฉ๐ฎ ๐ข๐๐๐ง๐ค๐จ๐๐ค๐ฅ๐ฎ ๐จ๐๐ข๐ช๐ก๐๐ฉ๐๐ค๐ฃ๐จโยตStack orchestrates the complete pipeline with ease. ๐๐๐๐ ๐๐๐๐๐ ๐๐ ๐๐๐๐๐๐๐: โจ โข Multi-technique microscopy support (๐ฆ๐ง๐ , ๐๐๐ง๐ฆ, ๐ง๐๐ , ๐๐๐ ) with GPU acceleration ๐ฏ โข Intelligent session management for seamless structure reuse ๐ โข Natural language query interface paired with Materials Project database ๐ โข Both CLI and interactive web interface with real-time progress tracking ๐ฅ๏ธ ๐๐๐๐๐ ๐๐๐ ๐๐๐๐: ๐ ๏ธ - LangGraph for multi-agent orchestration - MACE-MP/UMA universal ML potential for rapid structure relaxation using TorchSim - GPAW DFT, abTEM, and ppafm for physics-accurate simulations - FastAPI + React frontend
๐ฌMeet ยต๐๐ญ๐๐๐คโan AI-powered platform that democratizes atomistic microscopy simulations! ๐
๐ฅLLM-driven structure generation โ ML-based relaxation โ GPU-accelerated simulations
Big thanks to our team๐ค & hackathon organizers! ๐
Related links in thread๐
#AI #Science #Microscopy #llmagents #hackathon
Since the advent of various pre-trained large language models, extracting structured knowledge from scientific text has experienced a revolutionary change compared with traditional machine learning or natural language processing techniques. Despite these advances, accessible automated tools that allow users to construct, validate, and visualise datasets from scientific literature extraction remain scarce. We therefore developed ComProScanner, an autonomous multi-agent platform that facilitates the extraction, validation, classification, and visualisation of machine-readable chemical compositions and properties, integrated with synthesis data from journal articles for comprehensive database creation. We evaluated our framework using 100 journal articles against 10 different LLMs, including both open-source and proprietary models, to extract highly complex compositions associated with ceramic piezoelectric materials and corresponding piezoelectric strain coefficients (d33), motivated by the lack of a large dataset for such materials. DeepSeek-V3-0324 outperformed all models with a significant overall accuracy of 0.82. This framework provides a simple, user-friendly, readily-usable package for extracting highly complex experimental data buried in the literature to build machine learning or deep learning datasets.
๐1st first-author paper from PhD is out as preprint!
๐๐จ๐ฆ๐๐ซ๐จ๐๐๐๐ง๐ง๐๐ซ: A multi-agent based framework for composition-property structured data extraction from scientific literature
๐https://arxiv.org/abs/2510.20362
๐ปhttps://github.com/slimeslab/comproscanner
๐https://slimeslab.github.io/ComProScanner
Our multimodal follow-up to ChemBench. Our team went to the lab to create images to challenge leading vision language models.
Check the paper arxiv.org/abs/2411.16955 to learn more.
We are hiring (resharing appreciated)!
Given recent successful grant applications (I got my SNSF Starting Grant ๐), we are extending the LIAC team with multiple openings (PhD/postdoc) for 2025.
Apply now (deadline: December 20th) by filling in this form: forms.fillout.com/t/eq5ADAw3kkus.
#ChemSky
For those of you looking for a big helping of LLMs for Thanksgiving, here you go! ๐ค๐ฆ
๐ arxiv.org/abs/2411.15221
We release 34 examples demonstrating applications of LLMs in materials science and chemistry across:
๐ถmolecular and material property prediction;
๐ทmolecular and material design;
...
