The paper proposes a multi-dimensional evaluation framework to assess EEG foundation models under realistic low-resource conditions, finding that while these models excel in long-context tasks, their…

EvoBrain proposes a dynamic, cross-task continual learning framework to overcome the limitations of task-specific EEG decoding, enabling unified and scalable brain-computer interfaces.

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

This paper benchmarks five positional encoding strategies for transformer-based EEG foundation models, concluding that the optimal encoding is task-dependent and no single strategy is universally supe…

EVA-Net proposes a two-stage framework that uses action videos as semantic priors to achieve strong subject-independent EEG motor decoding, significantly outperforming text-based methods.

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

The paper introduces Geodesic Flow Matching, a manifold-aware denoising technique that adapts Riemannian transport dynamics to accurately clean high-dimensional structured representations like Spatial…

MASER is a lightweight framework that dynamically routes a shared Vision-Language Model (VLM) to the most appropriate modality-specific adapter (e.g., point cloud, RGB) based on the input question, si…

The paper analyzes the routing behavior of Mixtral MoE under benign and harmful prompts using activation and gradient signals, finding that safety-relevant routing is subtle, depth-dependent, and dist…

The paper introduces a distributional framework using Wasserstein distance to unify the semantic comparison of sparse autoencoder features across different layers and to automatically compress large f…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

The paper proposes a local perturbation theory showing that cross-domain interference in multi-domain RL occurs via a low-dimensional shared conflict subspace, which can be selectively mitigated by sh…

The paper proposes the Morlet Spectral Transformer (MST), a novel architecture that effectively decodes cross-subject emotion from EEG by designing specialized spectral and spatial representations, ou…

CaMBRAIN introduces a novel Mamba-based State Space Model (SSM) for real-time, continuous EEG inference, achieving state-of-the-art results with significantly higher throughput than existing methods.

The paper introduces Complexity-Balanced Splitting (CBS), a framework that efficiently allocates model capacity across the diffusion timeline by focusing computational resources on the most complex ge…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong gene…

WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLM…