Emotion-Cause Pair Extraction (ECPE) aims to identify and extract emotion clauses and their corresponding cause clauses from unannotated emotional texts. Previous approaches primarily leveraged contextual features or attention weights as semantic information to enhance feature representations. However, these methods often overlook the additional causal information that external knowledge can bring to ECPE. Given the evident inferential relationship between emotions and their causes, we propose a novel model called Rhetorical Structure Theory and Inference-Aware Graph networks (RSTIAG) to address the challenges posed by ECPE. This model constructs a semantic dependency space grounded in discourse-level rhetorical structure theory and a symbolic reasoning space based on an inference-aware graph. By integrating the introduced knowledge through a space fusion co-attention mechanism and modeling the dependencies between these two spaces, the model enables clauses to simultaneously capture diverse knowledge from both spaces. Additionally, we enrich the information dimensions of emotion-cause pairs by instantiating the reasoning process from the perspectives of causality and implicit inference. To substantiate the effectiveness of our proposed RSTIAG model, we undertake comprehensive experiments. The results demonstrate that it significantly outperforms 11 baseline models on an English benchmark corpus, confirming its effectiveness.

Plant disease detection under complex field conditions remains a critical challenge for precision agriculture due to varying illumination, scale variations, subtle lesion patterns, and inter-class visual ambiguity. This study proposes MAFusionNet, a disease-aware hybrid vision framework integrating Mamba and Transformer architectures, with components explicitly designed for plant disease-specific challenges. The MAFusion Mixer operates parallel CS-Mamba and self-attention branches to simultaneously capture sequential lesion boundary evolution and global diseasecontext spatial relationships. The CS-Mamba branch employs the SS2D-LS Block with twodimensional selective scanning and Local-Selective enhancement for linear-complexity longrange modeling while preserving 2D lesion morphology. The PConv operator uses asymmetric directional kernels forming cross-shaped receptive fields to capture anisotropic disease patterns such as vein-aligned blights and directional rust streaks. We constructed PD40, a large-scale dataset with 80,369 expert-verified annotated images across 40 disease categories spanning eight major crops, with inter-annotator agreement Cohen’s κ = 0.874. Extensive experiments demonstrate that MAFusionNet achieves 94.7% mAP ⁵⁰ and 81.8% mAP ^50:95 on PD40, surpassing 25 state-of-the-art baselines including recent hybrid Mamba-Transformer detectors (CropMamba, HybridMamba, Mamba-DETR), with comprehensive ablation studies validating each component’s non-redundant contribution. Edge deployment analysis on NVIDIA Jetson hardware demonstrates practical feasibility: the compressed MAFusionNet-T-Lite variant (8.7M parameters) achieves 89.3% mAP ⁵⁰ at 18.4 FPS on Jetson Nano with 8.3W power consumption. The dataset and code are available at PD40-Dataset GitHub Repository.

A graph attention network-enhanced multi-agent proximal policy optimization (GAT-MAPPO) framework is proposed for cooperative guidance in adversarial engagement scenarios. A dynamic heterogeneous interaction graph is formulated over interceptors and targets at every decision epoch. Through a multi-head graph attention encoder, relational features capturing both inter-interceptor cooperation and target threat dynamics are adaptively aggregated. These graph-enriched observations are processed by a Centralized-Training, Decentralized-Execution (CTDE) MAPPO architecture, guided by a hierarchical reward function that mandates miss distance minimization, simultaneity of arrival consensus, multi-directional encirclement, and smooth control effort. Furthermore, the integration of a three-stage curriculum learning strategy allows for robust cooperative policy derivation across transitions from rectilinear to highly adaptive evasion patterns, eliminating the need for explicit rule engineering. Extensive Monte Carlo simulations confirm GAT-MAPPO’s superior performance: achieving $>95\%$ interception success rate in 4-vs.-4 scenarios and reducing mean simultaneity error by $41.4\%$ compared to the MAPPO baseline. Comprehensive ablation and sensitivity studies validate the critical roles played by graph attention encoding, reward hierarchy design, and progressive curriculum staging.

A graph attention network-enhanced multi-agent proximal policy optimization (GAT-MAPPO) framework is proposed for cooperative guidance in counter-attack/defense scenarios. A dynamic heterogeneous interaction graph is formulated over interceptors and targets at every decision epoch. Through a multi-head graph attention encoder, relational features capturing both inter-interceptor cooperation and target threat dynamics are adaptively aggregated. These graph-enriched observations are processed by a Centralized-Training, Decentralized-Execution (CTDE) MAPPO architecture, guided by a hierarchical reward function that mandates miss distance minimization, simultaneity of arrival consensus, multi-directional encirclement, and smooth control effort. Furthermore, the integration of a three-stage curriculum learning strategy allows for robust cooperative policy derivation across transitions from rectilinear to highly adaptive evasion patterns, eliminating the need for explicit rule engineering. Extensive Monte Carlo simulations confirm GAT-MAPPO’s superior performance: achieving >95% interception success rate in 4-vs-4 scenarios and reducing mean simultaneity error by 41.4% compared to the MAPPO baseline. Comprehensive ablation studies validate the critical roles played by graph attention encoding, reward hierarchy design, and progressive curriculum staging.

Object detection in remote sensing imagery remains challenging due to vast scale variations, complex backgrounds, and the prevalence of small, densely packed targets. Existing CNN-based detectors are limited by restricted receptive fields, while Transformer-based methods incur prohibitive computational overhead for high-resolution inputs. In this paper, we propose SFSMamba-DETR, a detection framework that integrates state space models with Dual-Scale Window Attention for efficient and accurate remote sensing object detection. Specifically, we design a Selective Feature Scanning (SFS) module that uses the Mamba-based 2D Selective Scan mechanism to model long-range spatial dependencies with linear computational complexity. To capture both fine-grained local patterns and broader contextual cues simultaneously, we introduce a Dual-Scale Window Attention (DSWA) mechanism that operates at two complementary window scales with multi-kernel convolution bridging. These modules are orchestrated within a Cross-scale Feature Aggregation Module (CFAM) that performs hierarchical multi-scale fusion in a hybrid encoder. Extensive experiments on three primary benchmarks (MAR20, UCAS-AOD, and the Jilin-1 Satellite Aircraft Detection Dataset), together with supplementary results on DOTA and DIOR, demonstrate that SFSMamba-DETR achieves strong detection accuracy while maintaining competitive inference speed.