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.
By Leona Hioki
arXiv:2512. 01208v5 Announce Type: replace-cross Abstract: In standard Transformer architectures, semantic importance is often conflated with activation magnitude, obscuring the geometric structure of latent representations.
By Alper Y{\i}ld{\i}r{\i}m, \.Ibrahim Y\"uceda\u{g}
arXiv:2605. 18079v2 Announce Type: replace Abstract: Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice.
By Moritz Br\"osamle, Stephan Eckstein
arXiv:2608. 11173v1 Announce Type: cross Abstract: The attention mechanism forms the foundation of many modern AI models such as the Transformer.
By Eric A. F. Reinhardt, Adam J. Hauser
arXiv:2608.30720v1 Announce Type: new
Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied...
By Kieran Murphy
arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.
By Joshua S. Schiffman
arXiv:2608. 14691v1 Announce Type: new Abstract: Sequence models are conventionally distinguished by their backbone, the mechanism that routes information across positions, such as attention or recurrence.
By Ahmed Nebli, Hadi Saadatdoorabi, Christopher Keibel, Kevin Yam
arXiv:2607. 08946v1 Announce Type: new Abstract: A transformer can be built from operators that are legible by construction -- bounded, named units that read as fuzzy set operations rather than dense activations -- but legibility must be pressed for during training, and the pressure has a failure mode.
By Mark Oskin
arXiv:2604. 10098v2 Announce Type: replace Abstract: As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains.
By Zunhai Su, Hengyuan Zhang, Wei Wu, Yifan Zhang, Yaxiu Liu, He Xiao, Qingyao Yang, Yuxuan Sun, Rui Yang, Chao Zhang, Jing Xiong, Hui Shen, Keyu Fan, Weihao Ye, Chaofan Tao, Taiqiang Wu, Zhongwei Wan, Tiantian Zhang, Bowen Yan, Zhen Li, Yiming Zhang, Congkai Xie, Yulei Qian, Yuchen Xie, Yik-Chung Wu, Hongxia Yang, Ngai Wong
arXiv:2510. 25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits.
By Rabin Adhikari
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.
By Alper Y{\i}ld{\i}r{\i}m
arXiv:2607. 22361v1 Announce Type: new Abstract: We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space models -- through the lens of the indexing primitive.
By Alexander Kozachinskiy, Vicente Opazo, Felipe Urrutia