condition on attributes

This work addresses the challenge of detecting generative AI–produced content. We propose an unsupervised, interpretable embedding-space analysis method: semantic embeddings of text or images are extracted using pre-trained large language or multimodal models; subsequently, dimensionality reduction (e.g., PCA) uncovers an intrinsic, low-dimensional distributional shift between AI-generated and human-created samples—rendering them highly separable without supervision. This phenomenon is systematically validated for the first time and endowed with human-interpretable semantic meaning (e.g., topic coherence, syntactic redundancy). Experiments across diverse generative models—including ChatGPT, Gemini, and Stable Diffusion—demonstrate that high-accuracy separation is achieved solely from raw embeddings and unsupervised projection, without fine-tuning, labeled data, or model-specific detectors. Our approach thus significantly enhances both generalizability and interpretability of AI-content detection.

This work clarifies the functional boundaries and necessity of core Transformer components—tokenization, embedding/un-embedding, masking, positional encoding, and padding—addressing widespread conceptual ambiguity in their mechanistic roles. Targeting ML engineers, we propose an incremental, invertibility-based analytical framework: using binary (0/1) sequences as probes, we systematically introduce each component via a “zero-one construction” and empirically validate its irreplaceability in the encode-decode pipeline. Implemented lightweightly in PyTorch, our framework supports manual attention matrix construction, explicit positional embedding injection, and interpretable mask design. Experiments demonstrate significantly improved conceptual accuracy among learners. Notably, we provide the first empirical verification that, in the absence of self-attention, positional encoding combined with padding alone suffices for basic length-aware tasks.

Conventional categorical encoding methods (e.g., one-hot) in industrial process modeling lack semantic expressiveness, failing to capture meaningful relationships among categories such as reactor types or operation sequences. Method: This paper introduces, for the first time, an NLP-inspired semantic-aware categorical embedding framework: category-specific semantic vectors are generated via pre-trained language models and subsequently projected into an interpretable low-dimensional space using PCA or UMAP. Contribution/Results: Unlike conventional encodings, the proposed method explicitly models semantic distances between categories and enables quantitative feature importance analysis. Evaluated on an industrial case study involving cutting tool coatings, it achieves significant predictive performance gains. Moreover, it natively supports heterogeneous inputs—integrating both categorical and numerical features—thereby overcoming a fundamental limitation of existing encoding paradigms that cannot represent categorical similarity.

Traditional engineering design relies heavily on costly simulations, while existing data-driven approaches often overlook the parametric nature and design semantics of CAD models, limiting their integration into design workflows and interpretability. This work proposes Attribute Feature Graphs (AFGs), which, for the first time, encode native CAD features—such as extrusions and ribs—as graph nodes, with directed edges representing geometric and dependency relationships. This representation preserves design intent while enabling end-to-end learning with graph neural networks (GNNs). Evaluated on the CarHoods10K dataset, the resulting GNN surrogate model achieves prediction accuracy comparable to state-of-the-art methods and supports direct feature editing within CAD environments with real-time performance feedback. Crucially, the approach provides traceability and interpretability by linking predictions back to specific design features.

Existing feature engineering approaches suffer from three fundamental limitations: poor interpretability, weak generalizability, and inflexible strategies—hindering practical deployment across diverse scenarios. To address these challenges, this paper proposes the first large language model (LLM)-driven dynamic adaptive feature generation paradigm. Our method integrates task-aware prompting with semantic modeling of the feature space, enabling real-time, interpretable, and controllable feature generation tailored to both data characteristics and task requirements. It ensures cross-modal and cross-task generality while maintaining full transparency in the feature generation process. Extensive experiments on multiple structured and unstructured data tasks demonstrate that features generated by our approach improve feature quality by 23.6% and boost downstream model performance by an average of 11.4%, significantly outperforming conventional automated feature engineering methods.

This study addresses the limitation of traditional encoding schemes—such as one-hot encoding—in capturing fine-grained semantic relationships among architectural component subtypes, which hinders semantic understanding in artificial intelligence applications within the AECO (Architecture, Engineering, Construction, and Operations) domain. To overcome this, the authors propose a novel semantic encoding approach that integrates large language model (LLM) embeddings with Matryoshka-compressed representations. Specifically, they combine LLM-generated semantic vectors—derived from GPT and LLaMA—with GraphSAGE, a graph neural network, for semantic classification across 42 architectural component categories. Experimental results demonstrate that the proposed method substantially outperforms the one-hot baseline, with the compressed LLaMA-3 embeddings achieving a weighted F1 score of 0.8766—an improvement of approximately 2.9%—while effectively preserving fine-grained semantic relationships and enabling efficient modeling.

This study addresses the prevailing gap in AI education, which emphasizes model development while neglecting system engineering practices, leaving students ill-equipped to handle real-world challenges such as architectural design, deployment, and monitoring. To bridge this gap, the authors implemented a master’s-level course in which students built a movie recommendation system under realistic constraints, with a focus on integrating AI components into robust software systems, adopting data-driven machine learning practices, and cultivating systems-level thinking. Using a mixed-methods approach—combining analysis of student project artifacts with survey data—the research evaluates learners’ performance in architectural decision-making, integration of heterogeneous models, and adaptation to evolving requirements. Findings reveal common difficulties students encounter in AI system engineering and demonstrate the course’s effectiveness in addressing critical deficiencies in AI engineering education and enhancing systems-aware competencies.

This work addresses the limitation of current large language models in generating industrially relevant, complex CAD programs due to insufficient geometric diversity in their training data. Inspired by industrial design workflows, the authors propose a novel data augmentation approach that jointly conditions the generative process on both the modeling sequence and a reference surface, enabling large language models to produce parametric CAD programs incorporating spline-based organic geometric features. This method effectively compensates for the scarcity of organic shapes in existing open-source datasets, yielding synthetic samples that exhibit substantially greater geometric diversity and a higher proportion of organic structures—aligning more closely with real-world industrial design standards—and demonstrably enhance the training efficacy of downstream models.

This work addresses the tight coupling between design intent and printer-specific representations in heterogeneous manufacturing, which hinders cross-platform reuse. The authors propose a novel compiler architecture that models fabrication-aware design as a staged, type-directed lowering process, decoupling source design, attribute translation, and backend compilation to enable manufacturing-agnostic expression. Introducing compiler paradigms to heterogeneous manufacturing for the first time, the approach unifies volumetric information—such as material composition, hardness, and color—through implicit geometry and typed spatial attribute fields, automatically generating voxel stacks, G-code, or slicer projects. Experiments demonstrate successful fabrication of complex objects embedding CT data, Shore hardness fields, and full-color fields on both material jetting and extrusion platforms, validating cross-process reusability. The accompanying Python toolkit is publicly released.