Ni Li

Industrial standards are the basic specifications for the whole lifecycle management of complex products, including design, manufacturing, maintenance, remanufacturing, and recycling. As multidisciplinary knowledge is required for complex products, cross-standard reasoning and clause-level traceability become imperative for decision-support systems. However, existing retrieval-augmented generation (RAG) methods suffer from incomplete standard-scoped evidence retrieval, identifier and evidence-identity heterogeneity, and a mismatch between open-answer correctness and clause-level traceability. To overcome these drawbacks, this paper proposes a Source-Clause-Triple Anchored RAG (SCT-RAG) method specifically designed for traceable industrial standard retrieval. It establishes bidirectional bindings among source standards, clauses, and extracted knowledge triples using unique clause identifiers. Then, a standard-aware router classifies queries into single-standard, cross-standard, and correlation categories. Based on this classification, a standard-anchored retriever combines standard-number-directed lookup, within-standard dense enrichment, and clause-linked knowledge graph (KG) traversal to improve evidence coverage within the identified standard scope. Furthermore, an identity-preserving reranking and generation stage refines the evidence while preserving the unique clause identity of every candidate, and restricts the generator to cite only identifiers exposed in the retrieved context. Experiments on a 200-question test set over a corpus of 200 industrial standards show that the proposed method achieves a clause-level Hit@5 of 0.775, an answer accuracy of 0.755, and a Citation F1 of 0.616 under predicted routing, outperforming eight retrieval-augmented baselines and a closed-book control.

Coordinating multiple unmanned aerial vehicles (UAVs) for cooperative missions requires agents that perceive their environment, reason about objectives, and generate joint actions. Vision–language–action (VLA) models unify these capabilities but lack a principled source of multi-agent training data and suffer from a training–inference discrepancy in closed-loop control. We propose MiniUAV-VLA, a compact centralized VLA controller for simulated multi-UAV search-and-elimination based on multi-agent reinforcement learning (MARL) expert distillation. A QMIX expert policy achieving 100% mission success generates multimodal demonstrations pairing rendered tactical map images with structured textual state prompts. A 158 M-parameter VLA model with approximately 65 M trainable parameters in the MiniMind-3V backbone and vision projection is fine-tuned with a multi-agent discrete action head that jointly predicts actions for all UAVs in a single forward pass. We identify a training–inference feature mismatch in behavior cloning and address it via prompt-end action pooling, which extracts action-relevant hidden states at the user–prompt boundary rather than after the generated response. In closed-loop evaluation with four drones and six mobile targets averaged over five evaluation seeds, MiniUAV-VLA reaches 74.4 ± 4.6% mission success against 9.4 ± 2.1% for a random policy and 16.2 ± 3.2% for an observation-limited greedy baseline. Across five independent training runs, prompt-end action pooling improves mean closed-loop success from 40.6% to 76.2% over the last-token alternative. These results support MARL expert distillation as a data-efficient route to compact multi-agent VLA control in this simulated setting.

We present a high-resolution 3D facial dataset focused on East Asian participants, designed to provide consistent topology and expression diversity. The dataset includes 98 individuals (18–30 years) and captures neutral faces, six basic emotions, and nine Facial Action Coding System (FACS)-based Action Units (AUs). Each 3D mesh is acquired under a standardized protocol. Synchronized multi-view RGB images are available only for a subset of participants who provided additional consent. To ensure structural consistency across subjects and expressions, we developed a processing pipeline combining FLAME-based expression fitting with Edge-Constrained Non-rigid Iterative Closest Point (Edge-NICP). The resulting meshes share unified topology and vertex correspondence, enabling direct point-to-point comparisons across conditions. Rich annotations, including facial landmarks, verified AU labels, and vertex-level deformation fields, accompany the dataset. Together, these resources may facilitate research in computer graphics, human–computer interaction, and cross-modal studies that benefit from expression-rich, topology-standardized 3D face data.

Deep reinforcement learning (DRL) provides a powerful approach for autonomous decision-making behavior modeling in complex dynamic environments. However, its black-box nature restricts practical deployment, as interpretable and trustworthy models are often required in real-world applications. Existing interpretable methods often face a trade-off between transparency and decision performance. To address this limitation, this paper proposes a Clustering-Guided Fuzzy Inference System (CG-FIS) that leverages behavioral data collected from a trained DRL policy to derive inherently interpretable behavior models. Specifically, we integrate a density-based clustering approach (DBSCAN) to automatically identify underlying behavioral patterns within the data, from which fuzzy rules are systematically derived to support interpretable decision-making. The resulting CG-FIS provides semantic-level explanations through a transparent base of IF-THEN fuzzy rules. A modeling pipeline is further developed based on CG-FIS, incorporating state space refinement through Independent Component Analysis (ICA) to handle complex multidimensional tasks, along with iterative parameter tuning via Particle Swarm Optimization (PSO) to enhance the effectiveness of CG-FIS. The proposed method is validated on four standard RL benchmarks and a domain-specific case study, demonstrating superior decision performance compared to widely adopted interpretable behavior models. Experimental results demonstrate that CG-FIS generates both effective and interpretable fuzzy policies.