[2603.22721] HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment

Computer Science > Artificial Intelligence arXiv:2603.22721 (cs) [Submitted on 24 Mar 2026] Title:HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment Authors:Sangmin Jo, Wootaek Jeong, Da-Woon Heo, Yoohwan Hwang, Heung-Il Suk View a PDF of the paper titled HyFI: Hyperbolic Feature Interpolation for Brain-Vision Alignment, by Sangmin Jo and 4 other authors View PDF HTML (experimental) Abstract: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 ...