5 papers
PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
Botong Zhao, Fang Yu, Tim Yu +3
Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not exp…
ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarios
Botong Zhao, Qijun Shi, Shujing Lyu +1
Existing industrial anomaly detection methods mainly determine whether an anomaly is present. However, real-world applications also require discovering and classifying multiple ano…
LithoSeg: A Coarse-to-Fine Framework for High-Precision Lithography Segmentation
Xinyu He, Botong Zhao, Bingbing Li +3
Accurate segmentation and measurement of lithography scanning electron microscope (SEM) images are crucial for ensuring precise process control, optimizing device performance, and…
Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learning
Botong. Zhao, Xubin. Wang, Shujing. Lyu +1
Integrated circuit manufacturing is highly complex, comprising hundreds of process steps. Defects can arise at any stage, causing yield loss and ultimately degrading product reliab…
Unsupervised Integrated-Circuit Defect Segmentation via Image-Intrinsic Normality
Botong Zhao, Qijun Shi, Shujing Lyu +1
Modern Integrated-Circuit(IC) manufacturing introduces diverse, fine-grained defects that depress yield and reliability. Most industrial defect segmentation compares a test image a…