Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Srinivas, Sakhinana Sagar, Sannidhi, Geethan, Gangasani, Sreeja, Ravuru, Chidaksh, Runkana, Venkataramana
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909298075893760
author Srinivas, Sakhinana Sagar
Sannidhi, Geethan
Gangasani, Sreeja
Ravuru, Chidaksh
Runkana, Venkataramana
author_facet Srinivas, Sakhinana Sagar
Sannidhi, Geethan
Gangasani, Sreeja
Ravuru, Chidaksh
Runkana, Venkataramana
contents Characterizing materials using electron micrographs is crucial in areas such as semiconductors and quantum materials. Traditional classification methods falter due to the intricatestructures of these micrographs. This study introduces an innovative architecture that leverages the generative capabilities of zero-shot prompting in Large Language Models (LLMs) such as GPT-4(language only), the predictive ability of few-shot (in-context) learning in Large Multimodal Models (LMMs) such as GPT-4(V)ision, and fuses knowledge across image based and linguistic insights for accurate nanomaterial category prediction. This comprehensive approach aims to provide a robust solution for the automated nanomaterial identification task in semiconductor manufacturing, blending performance, efficiency, and interpretability. Our method surpasses conventional approaches, offering precise nanomaterial identification and facilitating high-throughput screening.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models
Srinivas, Sakhinana Sagar
Sannidhi, Geethan
Gangasani, Sreeja
Ravuru, Chidaksh
Runkana, Venkataramana
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Characterizing materials using electron micrographs is crucial in areas such as semiconductors and quantum materials. Traditional classification methods falter due to the intricatestructures of these micrographs. This study introduces an innovative architecture that leverages the generative capabilities of zero-shot prompting in Large Language Models (LLMs) such as GPT-4(language only), the predictive ability of few-shot (in-context) learning in Large Multimodal Models (LMMs) such as GPT-4(V)ision, and fuses knowledge across image based and linguistic insights for accurate nanomaterial category prediction. This comprehensive approach aims to provide a robust solution for the automated nanomaterial identification task in semiconductor manufacturing, blending performance, efficiency, and interpretability. Our method surpasses conventional approaches, offering precise nanomaterial identification and facilitating high-throughput screening.
title Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2408.13621