Fine-tuning Qwen3-VL-32B-Instruct on a curated set of 13k fracture images yields a specialist model achieving 0.92 precision on morphology recognition, outperforming the base model and several proprietary VLMs on a 100-image manual benchmark.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cond-mat.mtrl-sci 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
GPU-PF and PRISMS-PF phase-field codes produce consistent predictions for dendritic morphology, primary spacing, and tip dynamics in 2D and 3D simulations of alloy solidification at experimentally relevant scales.
citing papers explorer
-
Fine-tuning a vision-language model for fracture-surface morphology recognition
Fine-tuning Qwen3-VL-32B-Instruct on a curated set of 13k fracture images yields a specialist model achieving 0.92 precision on morphology recognition, outperforming the base model and several proprietary VLMs on a 100-image manual benchmark.
-
Benchmarking of Massively Parallel Phase-Field Codes for Directional Solidification
GPU-PF and PRISMS-PF phase-field codes produce consistent predictions for dendritic morphology, primary spacing, and tip dynamics in 2D and 3D simulations of alloy solidification at experimentally relevant scales.