The study investigates how the geometry of representations in artificial neural networks can be steered to improve bidirectional alignment with biological neural responses. By applying spectral regularization during training of self‑supervised contrastive vision models, the authors increased reverse predictivity by 55% while only modestly reducing forward predictivity. The changes also lowered effective dimensionality and reorganized the shared subspace, making forward and reverse predictivity more symmetric at certain spectral exponents.
By Samuel Kostousov, Abhinn Kaushik, Brokoslaw Laschowski
arXiv:2608. 08309v1 Announce Type: cross Abstract: We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy.
By Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki
arXiv:2605. 30556v2 Announce Type: replace Abstract: CORRECTION (August 2026): the central finding of this paper is not supported.
By Nils Leutenegger
arXiv:2503. 21796v2 Announce Type: replace-cross Abstract: Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence.
By Alexander Ororbia, Karl Friston, Rajesh P. N. Rao
arXiv:2607. 16295v1 Announce Type: cross Abstract: Mechanistic interpretability has made significant strides in understanding neural network representations, with sparse dictionary learning (SDL) methods, most prominently sparse autoencoders, as a central paradigm.
By Yiming Tang, Qinglin Qi, Zhaoqian Yao, Harshvardhan Saini, Dianbo Liu
arXiv:2607. 02386v1 Announce Type: cross Abstract: While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood.
By Kaustubh Kapil, Kishor P. Upla
arXiv:2603. 01568v2 Announce Type: replace Abstract: Efficient coding theory predicts that biological perceptual systems compress sensory input optimally under resource constraints, with the systematic structure of errors reflecting the geometry of that compression.
By Leyla Roksan Caglar, Pedro A. M. Mediano, Baihan Lin
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
By Hossein Adeli, Seoyoung Ahn, Andrew Luo, Mengmi Zhang, Nikolaus Kriegeskorte, Gregory Zelinsky
arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.
By Davide Caffagni, Alberto Compagnoni, Federico Melis, Sara Sarto, Pier Luigi Dovesi, Mark Granroth-Wilding, Marcella Cornia, Lorenzo Baraldi
arXiv:2606. 28399v1 Announce Type: cross Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour.
By Can Demircan, Marcel Binz, Alireza Modirshanechi, Eric Schulz
arXiv:2502. 14424v3 Announce Type: replace-cross Abstract: Most self-supervised learning objectives defend against collapse but leave the target representation law unspecified.
By Yuling Jiao, Wensen Ma, Defeng Sun, Hansheng Wang, Yang Wang
arXiv:2606. 05173v1 Announce Type: cross Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure.
By Aimen Boukhari