Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception.

Ensemble learning is a pivotal machine learning strategy that combines multiple base learners to achieve prediction accuracy surpassing that of any individual model. Despite its effectiveness, large-scale ensemble learning consumes a considerable amount of resources. Ensemble pruning addresses this issue by selecting a subset of base learners from the original ensemble to form a sub-ensemble, while maintaining or even improving the performance of the original model. However, existing ensemble pruning strategies often rely on heuristic solutions that may fail to capture complex interactions among base learners. To address this limitation, in this work, we model the base learners in an ensemble as a weighted and attributed graph, where node features represent characteristics of each learner and edge weights represent relationships between the base learners. Leveraging this representation, we propose a novel ensemble pruning method based on graph neural networks (GNNs). Our approach incorporates specialized GNN architectures designed for bagging and boosting ensembles. Experimental results demonstrate that our method not only improves prediction accuracy but also significantly reduces inference time across diverse datasets. Our implementation is available at the anonymous repository: https://github.com/TechnologyAiGroup/GRE.