A blast at a fireworks factory in China's Hunan province has killed 21 people and left 61 wounded, according to state media. The explosion at the Changsha Liuyang Huasheng Fireworks plant happened at around 16:40 local time (08:40 GMT) on Monday, in the city of Liuyang, leading rescuers to evacuate everyone within a 3km (1.9mi) radius of the plant. Authorities deployed nearly 500 personnel to conduct search and rescue operations and treat the injured, while robots were used to help find those trapped within the building. Police, who are investigating the cause of the blast, have taken control measures against the person in charge of the fireworks company, Chinese state media reported. Authorities said that two gunpowder warehouses within the factory area posed a high risk amid rescue efforts, state media reported.

Electroencephalography (EEG)-based emotion recognition suffers from severe performance degradation when models are transferred across heterogeneous datasets due to physiological variability, experimental paradigm differences, and device inconsistencies. Existing domain adversarial methods primarily enforce global marginal alignment and often overlook class-conditional mismatch and decision boundary distortion, limiting cross-corpus generalization. In this work, we propose a unified Prototype-driven Adversarial Alignment (PAA) framework for cross-corpus EEG emotion recognition. The framework is progressively instantiated in three configurations: PAA-L, which performs prototype-guided local class-conditional alignment; PAA-C, which further incorporates contrastive semantic regularization to enhance intra-class compactness and inter-class separability; and PAA-M, the full boundary-aware configuration that integrates dual relation-aware classifiers within a three-stage adversarial optimization scheme to explicitly refine controversial samples near decision boundaries. By combining prototype-guided subdomain alignment, contrastive discriminative enhancement, and boundary-aware aggregation within a coherent adversarial architecture, the proposed framework reformulates emotion recognition as a relation-driven representation learning problem, reducing sensitivity to label noise and improving cross-domain stability. Extensive experiments on SEED, SEED-IV, and SEED-V demonstrate state-of-the-art performance under four cross-corpus evaluation protocols, with average improvements of 6.72\%, 5.59\%, 6.69\%, and 4.83\%, respectively. Furthermore, the proposed framework generalizes effectively to clinical depression identification scenarios, validating its robustness in real-world heterogeneous settings. The source code is available at \textit{https://github.com/WuCB-BCI/PAA}

These features are then fed into a V alue Classification Network (VCN) which directly generates classification solutions.

Appendix for "Episodic Multi-T ask Learning with Heterogeneous Neural Processes" In this section, we list frequently asked questions from researchers who help proofread this manuscript. As shown in Table 1, we use "Heterogeneous tasks" to distinguish the different branches of multi-task Meanwhile, "Episodic training" is used to describe the data-feeding strategy. Thus, "Heterogeneous tasks" is not available here (-). In episodic multi-task learning, we restrict the scope of the problem to the case where tasks in the same episode are related and share the same target space. This also implies that tasks with the same target space are related.

Despite efficiencyimprovements, existing methods overlook themisguidance in anchors learning induced by partial missing samples,i.e., the absence of samples results in shift of learned anchors, further leading to sub-optimal clustering performance.

Accordingly, extensive evaluations demonstrate the significance of our proposal and its scalability to multimodal large models in boosting robustness.

Step 2. The deduction in Step 1 can be iterated repeatedly due to the symmetry of