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.
arXiv:2608. 11173v1 Announce Type: cross Abstract: The attention mechanism forms the foundation of many modern AI models such as the Transformer.
arXiv:2606. 00926v1 Announce Type: new Abstract: Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, attention-based models distribute it.
arXiv:2607. 19390v1 Announce Type: new Abstract: A recent report finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) substantially improves noisy associative recall.
arXiv:2607. 19368v1 Announce Type: new Abstract: Long-prompt inference remains expensive because prefill attention scales quadratically with sequence length.
arXiv:2606. 12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates.
arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.
arXiv:2608. 11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
arXiv:2604. 13082v2 Announce Type: replace-cross Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood.
arXiv:2606. 03938v1 Announce Type: cross Abstract: Multi-epoch training is becoming the standard now that compute is growing faster than the supply of high-quality text.
arXiv:2504. 05336v4 Announce Type: replace-cross Abstract: A recurring weakness in quantum machine learning (QML) is that reported ``quantum advantages'' are seldom tested against a \emph{capacity-matched} classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it.
arXiv:2606. 01294v1 Announce Type: cross Abstract: Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tasks.