3 papers
cs.CV2026
Hi-DREAM: Brain-Inspired Hierarchical Diffusion for fMRI-to-Image Reconstruction via ROI Encoder and VisuAl Mapping
Guowei Zhang, Yun Zhao, Kai Sun +4
Reconstructing natural images from fMRI requires bridging neural activity with both the structural and semantic representations used by modern generative models. Existing diffusion…
cs.LG2026
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Binghang Lu, Zheyuan Deng, Runyu Zhang +6
A central challenge in continual learning for large language models (LLMs) is catastrophic forgetting, where adapting to new tasks can substantially degrade performance on previous…
cs.LG2026
CFSPMNet: Cross-subject Fourier-guided Spatial-Patch Mamba Network for EEG Motor Imagery Decoding in Stroke Patients
Xiangkai Wang, Yun Zhao, Dongyi He +5
Motor imagery electroencephalography (MI-EEG) decoding offers a non-invasive route for post-stroke rehabilitation, but cross-patient use remains difficult because pathological neur…