Building-MLLM, with PIE, GPR, fixed prefix and multi-dimensional LoRA plus a 37k-pair synthetic dataset, reaches 88/65/68 % on recognition, captioning and multi-engineering QA for 47 indoor component categories.
Title resolution pending
1 Pith paper cite this work, alongside 62 external citations. Polarity classification is still indexing.
1
Pith paper citing it
62
external citations · OpenAlex
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Geometric Labels to Semantic Understanding of Indoor Building Components Using Multimodal Large Language Models
Building-MLLM, with PIE, GPR, fixed prefix and multi-dimensional LoRA plus a 37k-pair synthetic dataset, reaches 88/65/68 % on recognition, captioning and multi-engineering QA for 47 indoor component categories.