3 papers
cs.LG2025
Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
Daniel Gallo Fernández
Sequence-to-sequence models have become central in Artificial Intelligence, particularly following the introduction of the transformer architecture. While initially developed for N…
cs.SD2025
Linear RNNs for autoregressive generation of long music samples
Konrad Szewczyk, Daniel Gallo Fernández, James Townsend
Directly learning to generate audio waveforms in an autoregressive manner is a challenging task, due to the length of the raw sequences and the existence of important structure on…
math.NT2025
Patterns in Growth and Distribution of Unbounded Prime Number Walks
Alberto Fraile, Daniel Fernández, Roberto Martínez +1
In our previous work, we defined a prime walk (PW) on a square grid and presented several intriguing numerical results. Here, we demonstrate the main conjecture presented there, na…