Decoding neural activity into natural speech is a frontier in cognitive neuroscience and brain-computer interfaces. Existing methods overlook two critical issues when decoding continuous long-sequence speech: the pronounced inter-subject variability and substantial temporal fluctuations within individual EEG signals, as well as the inherent transverse sparsity present in acoustic features. To address these issues, this paper proposes DA2Mel, a dual-dynamic adaptive network that enhances the perception of non-stationary neural signals. The Dynamic Subject-Specific Memory integrator (DSSM) forms an adaptive closed loop using identity-aware memory and momentum updating. It adapts to EEG distribution shifts from inter- and intra-subject variations, aligns with dynamic physiological states, and ensures long-term robustness. The Dual-Pathway Spatial-Channel Processor (DP-SCP) extracts critical channel information, fuses multi-scale spatial features, and bridges global trends and local details. In addition, the Stacked Fine-Grained Module (SFGM) employs a content-aware adaptive mechanism, fusing local convolutions with partial Top- \(k\) sparse attention. By dynamically reconstructing representation weights based on the instantaneous sparsity of acoustic features, SFGM distills pivotal characteristics and optimizes semantics under noise. Experimental results on the SparrKULee dataset demonstrate that DA2Mel outperforms state-of-the-art methods in both the Held-out Stories and Held-out Subjects settings, validating the superiority of our framework for continuous speech decoding.
Despite substantial progress in managing uncertainty in software-intensive systems, existing methods often treat uncertainty sources independently and provide limited support for understanding their combined effects. When multiple uncertainties propagate through system elements and converge at shared variables, models, or decision points, they may interact in ways that alter system behavior, compromise requirements, or invalidate assurance arguments. This challenge, referred to as the uncertainty interaction problem, remains insufficiently understood. This roadmap paper reports the outcomes of the NII Shonan Seminar No. 232 on Uncertainty Interaction in Software-Intensive Systems (UNISON), held in March 2026. It develops a shared conceptual vocabulary for distinguishing uncertainty sources, propagation, confluence, interaction, and relevance; proposes an abstract workflow for identifying, filtering, and assessing relevant uncertainty interactions; and introduces a lifecycle-oriented framework for characterizing and selecting mitigation strategies. Building on these foundations, the paper organizes open challenges into a staged research roadmap spanning conceptual consolidation, reusable methods, engineering integration, validation, tooling, and community adoption. The roadmap provides a common reference point for researchers and practitioners working across software engineering, self-adaptive systems, control, artificial intelligence, formal methods, and assurance.
Hybrid brain-computer interfaces combining electroencephalography and functional near-infrared spectroscopy utilize neurovascular coupling to improve decoding. Current fusion strategies rely on shallow aggregation or complex attention, which struggle to capture complex temporal dynamics and complex dependencies in long sequences. Moreover, static models lack online calibration for sensor failures or non-stationary noise, causing significant performance drops. We propose the Multi-Scale Bidirectional Mamba with Test-Time Adaptation (MS-BiM-TTA) framework. The architecture employs a multi-scale frontend for heterogeneous feature extraction and bidirectional state-space models for efficient long-range intra-modal and inter-modal modeling with linear complexity. To ensure robustness, a customized test-time adaptation workflow utilizes two-level entropy filtering for update safety and mutual information sharing for autonomous representation reconstruction. Results show that MS-BiM-TTA significantly enhances accuracy and demonstrates superior resilience to modality missingness in both binary and fine-grained tasks.
