Despite advancements in Computer-Aided-Design (CAD) generation, direct generation of complex Boundary Representation (B-rep) CAD models remains challenging. The difficulty arises from the parametric nature of B-rep data, complicating the encoding and generation of its geometric and topological information. In this paper, we introduce BrepGiff, a lightweight generation approach for high-quality and complex B-rep based on 3D Graph Diffusion. First, we transfer B-rep models into 3D graphs representation. Specifically, BrepGiff extracts and integrates topological and geometric features to construct a 3D graph where nodes correspond to face centroids in 3D space, preserving adjacency and degree information. Geometric features are derived by sampling points in the UV domain and extracting face and edge features. BrepGiff then applies Graph Attention Network (GAT) to enforce topological constraints from local to global during the degree-guided diffusion process. With the 3D graph representation and diffusion process, BrepGiff significantly reduces the computational cost and improves the quality, thus achieving lightweight generation of complex models. Experiments show that BrepGiff can generate complex B-rep models (>100 faces) using only 2 RTX4090 GPUs, achieving state-of-the-art performance in B-rep generation.

Autism is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and sensory sensitivity. Functional magnetic resonance imaging (fMRI) is a commonly used brain imaging technique to obtain functional connectivity information in individuals with autism. However, the heterogeneity of functional MRI data from different imaging centers poses a modeling challenge, and the lack of interpretability in the models hinders the identification of biomarkers. To address these issues, this study proposes a deep learning model based on a dynamic functional connectivity matrix that extracts shared features across multiple centers, mitigates the multicentre problem, enhances the representation of the data, and combines features from multiple pathways to capture a comprehensive view of brain connectivity patterns. In addition, two complementary approaches are designed to enhance the interpretability of the model and further explore the presence of biomarkers by analyzing changes in important features of the model. The code will be released soon.

In this paper, we present an energy-efficient strong physical unclonable function (PUF) based on subthreshold inverters (STIs) that are regulated by a native NMOS transistor. Two groups of STIs can be dynamically regrouped to 4 stages according to the provided challenge, with each stage having different number of STIs connected in parallel. By adopting the first two stages as the entropy source and the last two stages for generating the PUF bits, the equivalent 4-stage STI chain can exhibit high reliability under largely varied temperature and supply voltage. Moreover, the proposed strong PUF implementation is validated using a standard 65-nm 1.2 V CMOS process. With the temperature and supply voltage changing from 0°C to 120°C and 0.7 V to 1.5 V, respectively, the worst-case bit error rate (BER) is reported to be 5.025%. Meanwhile, the energy consumption is simulated to be 0.26 pJ/bit at the maximum throughput of 10 Mb/s. Moreover, the proposed strong PUF shows high resilience to various machine learning (ML) attacks, including logistic regression, support vector machine and covariance matrix adaptation evolution strategy.