AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation

Zhuonan Wang, Zhenxuan Fan, Siwen Tan, Yu Zhong, Yuqian Yuan, Haoyuan Li, Hao Jiang, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use AMoE-LoRA instead of plain LoRA (ablation)MAU-GPT 4B · MAU-Set Open-Ended QABLEU-4: 0.4529 -> 0.4773Improved
use AMoE-LoRA instead of LoRAMoE (ablation)MAU-GPT 4B · MAU-Set Open-Ended QAROUGE-1: 0.6991 -> 0.7026Improved
use AMoE-LoRA instead of plain LoRA (ablation)MAU-GPT 4B · MAU-Set Open-Ended QAROUGE-L: 0.6449 -> 0.6531Improved
set 16 generalist experts with rank 4 (product fixed at 64) (ablation)MAU-GPT 4B · MAU-Set Open-Ended QAROUGE/BLEUImproved
domain-specific fine-tuning on MAU-Set vs general-purpose VLMsMAU-GPT 4B · MAU-Set Discriminative QA (Avg.)accuracy: 73.54 -> 82.12Improved
add more in-context shots to AnomalyGPTAnomalyGPT · MAU-Set Discriminative QA (Avg.)accuracy: 62.53 -> 66.03Improved
add more in-context shots to AnomalyGPTAnomalyGPT · MAU-Set Open-Ended QA (Avg., GPT-4o judged)accuracy: 21.61 -> 22.30No clear effect
scale LLaVA-1.5 from 7B to 13BLLaVA-1.5 · MAU-Set Discriminative QA (Avg.)accuracy: 43.61 -> 23.21Hurt
MAU-GPT 4B vs much larger 34B general models on MMADMAU-GPT 4B · MMAD (Average)accuracy: 61.41 vs 67.16 (LLaVA-NeXT-34B)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy