arXiv:2606. 17037v1 Announce Type: cross Abstract: Oppenheim and Lim (1981) showed that natural images stay recognizable when reconstructed from their Fourier phase alone, while the magnitude carries little of their identity.
arXiv:2610.01807v1 Announce Type: new Abstract: Reliable clinical deployment of deep medical image models is hindered by distribution shifts across scanners, sites, and acquisition protocols. Existin...
arXiv:2512. 23043v2 Announce Type: replace Abstract: Federated Averaging (FedAvg) often degrades under non-IID client data, but it remains unclear whether this degradation reflects the loss of client-learned representations or a failure to use representations that are still present.
arXiv:2609.26512v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge...
The paper introduces the Phase-Coherent Transformer (PCT), a complex-valued architecture that replaces traditional softmax attention with a real-valued, smooth gate applied to L2-normalised query-key similarities. PCT eliminates token competition, preserving phase information across layers, and demonstrates strong generalisation on a variety of mid-scale benchmarks, outperforming both standard softmax Transformers and other complex-valued counterparts. Experiments confirm that the gate design is essential: preserving negatively aligned phase components is crucial for performance, while violating these conditions leads to degradation or collapse on long-range tasks.
arXiv:2604. 07904v2 Announce Type: replace Abstract: Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding.
The paper investigates how neural representations maintain the structure of input changes, linking representation analysis with internal interventions. It characterises when transformations can be applied through an encoder, providing linear settings where defects depend on discarded information and detailing failure modes for rectifiers and harmonic carriers. Using colour as a case study, the authors show that hue orbits in frozen visual features concentrate most energy in the first two harmonics, that this structure is inherited from input and architecture, and that a compact, fixed‑action interface can read hue zero‑shot with low error on unseen shapes.
How neural representations preserve the structure of input changes connects representation analysis with internal intervention. We study operable representational content through compatible actions of...
arXiv:2608. 12408v1 Announce Type: cross Abstract: Representational similarity analysis (RSA) is increasingly used to ask which learning rules give convolutional networks brain-like representations.
arXiv:2606. 03493v1 Announce Type: cross Abstract: Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets.
arXiv:2609.24379v1 Announce Type: cross Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entan...
Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle many concepts in each neuron. Feature superposi...
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.