HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment

Computer Science > Artificial Intelligence [Submitted on 24 Mar 2026] HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment Sangmin Jo, Wootaek Jeong, Da-Woon Heo, Yoohwan Hwang, Heung-Il Suk Recent progress in artificial intelligence has encouraged numerous attempts to understand and decode human visual system from brain signals. These prior works typically align neural activity independently with semantic and perceptual features extracted from images using pre-trained vision models. However, they fail to account for two key challenges: (1) the modality gap arising from the natural difference in the information level of representation between brain signals and images, and (2) the fact that semantic and perceptual features are highly entangled within neural activity. To address these issues, we utilize hyperbolic space, which is well-suited for considering differences in the amount of information and has the geometric property that geodesics between two points naturally bend toward the origin, where the representational capacity is lower. Leveraging these properties, we propose a novel framework, Hyperbolic Feature Interpolation (HyFI), which interpolates between semantic and perceptual visual features along hyperbolic geodesics. This enables both the fusion and compression of perceptual and semantic information, effectively reflecting the limited expressiveness of brain signals and the entangled nature of these features. As a result, it facilitates better alignment between brain and visual features. We demonstrate that HyFI achieves state-of-the-art performance in zero-shot brain-to-image retrieval, outperforming prior methods with Top-1 accuracy improvements of up to +17.3% on THINGS-EEG and +9.1% on THINGS-MEG. Comments: 17 pages, 13 figures. Published in AAAI 2026 Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.22721 [cs.AI]   (or arXiv:2603.22721v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.22721 Focus to learn more Journal reference: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40, 2026 Related DOI: https://doi.org/10.1609/aaai.v40i7.37476 Focus to learn more Submission history From: Sangmin Jo [view email] [v1] Tue, 24 Mar 2026 02:35:54 UTC (18,674 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)