arXiv:2606. 11585v1 Announce Type: new Abstract: We introduce Kuramoto attention, a self-attention layer in which each hidden coordinate is an angle.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2606. 18694v1 Announce Type: new Abstract: A network of oscillators that synchronizes perfectly computes nothing further, so an attention architecture built from synchronization must locate its computation in structured departures from agreement.
arXiv:2606. 12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates.
arXiv:2601. 11618v2 Announce Type: replace-cross Abstract: Geometric Attention (GA) specifies an attention layer by four independent inputs: a finite carrier (what indices are addressable), an evidence-kernel rule (how masked proto-scores and a link induce nonnegative weights), a probe family (which observables are treated as admissible), and an anchor/update rule (which representative kernel is selected and how it is applied).
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
arXiv:2607. 09842v1 Announce Type: new Abstract: We investigate whether identity-specifying system prompts produce statistically distinguishable geometric fingerprints in the hidden-state trajectories of four open-weight transformer language models spanning four post-training regimes: no training (Gemma-4-E4B base), multimodal RLHF (Gemma-4-E4B-it), RL distillation (DeepSeek-R1-Distill-Qwen-7B), and SFT (Qwen2.
arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.