Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Context-length-independent universality is mathematically possible: a single causal transformer with fixed parameters can approximate functions across arbitrary token resolutions and context lengths, provided the input sequences satisfy mild Hölder regularity.
Spectral normalization schemes like Muon, previously justified empirically, now have a rigorous theoretical foundation via a novel family of Spectral Wasserstein distances, revealing their connection to gradient flows and metric spaces.
