Neurons++: A Unified Visual-Stream Framework for Image and Video Reconstruction from fMRI with Neural-to-Visual Interpretability

arXiv:2610.13763 · cs.CV · Submitted 2026-10-09 · Read on arXiv

cs.CV

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/xmed-lab/NeuronsPlusPlus

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Interpretability — 1× in this paper · explained in 15 episodes

Sources

• A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activity
• Brain Captioning: Decoding human brain activity into images and text
• A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
• fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Qwen2.5-VL Technical Report
• Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
• Decoupled Weight Decay Regularization
• Denoising Diffusion Implicit Models
• The Kinetics Human Action Video Dataset
• CVPR 2023 Text Guided Video Editing Competition

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models