{"ID":2847407,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.27128","arxiv_id":"2510.27128","title":"ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding","abstract":"Recent advances in neural decoding have enabled the reconstruction of visual experiences from brain activity, positioning fMRI-to-image reconstruction as a promising bridge between neuroscience and computer vision. However, current methods predominantly rely on subject-specific models or require subject-specific fine-tuning, limiting their scalability and real-world applicability. In this work, we introduce ZEBRA, the first zero-shot brain visual decoding framework that eliminates the need for subject-specific adaptation. ZEBRA is built on the key insight that fMRI representations can be decomposed into subject-related and semantic-related components. By leveraging adversarial training, our method explicitly disentangles these components to isolate subject-invariant, semantic-specific representations. This disentanglement allows ZEBRA to generalize to unseen subjects without any additional fMRI data or retraining. Extensive experiments show that ZEBRA significantly outperforms zero-shot baselines and achieves performance comparable to fully finetuned models on several metrics. Our work represents a scalable and practical step toward universal neural decoding. Code and model weights are available at: https://github.com/xmed-lab/ZEBRA.","short_abstract":"Recent advances in neural decoding have enabled the reconstruction of visual experiences from brain activity, positioning fMRI-to-image reconstruction as a promising bridge between neuroscience and computer vision. However, current methods predominantly rely on subject-specific models or require subject-specific fine-t...","url_abs":"https://arxiv.org/abs/2510.27128","url_pdf":"https://arxiv.org/pdf/2510.27128v1","authors":"[\"Haonan Wang\",\"Jingyu Lu\",\"Hongrui Li\",\"Xiaomeng Li\"]","published":"2025-10-31T03:05:04Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":607519,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2847407,"paper_url":"https://arxiv.org/abs/2510.27128","paper_title":"ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding","repo_url":"https://github.com/xmed-lab/ZEBRA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}