# A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding

arXiv: https://arxiv.org/abs/2511.02565 · HTML: https://mlsanity.com/paper/2511.02565/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data](https://mlsanity.com/paper/2403.11207/) (2024)
- [Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity](https://mlsanity.com/paper/2305.11675/) (2023)
- [MixCo: Mix-up Contrastive Learning for Visual Representation](https://mlsanity.com/paper/2010.06300/) (2020)
- [Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision](https://mlsanity.com/paper/1608.03425/) (2016)
- [CVPR 2023 Text Guided Video Editing Competition](https://mlsanity.com/paper/2310.16003/) (2023)
- [NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation](https://mlsanity.com/paper/2403.18211/) (2024)
- [MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction](https://mlsanity.com/paper/2404.12630/) (2024)
- [NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction](https://mlsanity.com/paper/2410.19452/) (2024)
- [fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding](https://mlsanity.com/paper/2311.00342/) (2023)
- [Brain Decodes Deep Nets](https://mlsanity.com/paper/2312.01280/) (2023)
- [Toward Generalizing Visual Brain Decoding to Unseen Subjects](https://mlsanity.com/paper/2410.14445/) (2024)
- [Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction](https://mlsanity.com/paper/2503.11167/) (2025)

## Built on by (most cited first, 3 of 3)

- [Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding](https://mlsanity.com/paper/2603.03312/) (2026)
- [Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction](https://mlsanity.com/paper/2605.14569/) (2026)
- [Neurons++: A Unified Visual-Stream Framework for Image and Video Reconstruction from fMRI with Neural-to-Visual Interpretability](https://mlsanity.com/paper/2610.13763/) (2026)

## Abstract (arXiv)

Subject-agnostic brain decoding, which aims to reconstruct continuous visual experiences from fMRI without subject-specific training, holds great potential for clinical applications. However, this direction remains underexplored due to challenges in cross-subject generalization and the complex nature of brain signals. In this work, we propose Visual Cortex Flow Architecture (VCFlow), a novel hierarchical decoding framework that explicitly models the ventral-dorsal architecture of the human visual system to learn multi-dimensional representations. By disentangling and leveraging features from early visual cortex, ventral, and dorsal streams, VCFlow captures diverse and complementary cognitive information essential for visual reconstruction. Furthermore, we introduce a feature-level contrastive learning strategy to enhance the extraction of subject-invariant semantic representations, thereby enhancing subject-agnostic applicability to previously unseen subjects. Unlike conventional pipelines that need more than 12 hours of per-subject data and heavy computation, VCFlow sacrifices only 7% accuracy on average yet generates each reconstructed video in 10 seconds without any retraining, offering a fast and clinically scalable solution. The source code will be released upon acceptance of the paper.