Recent Literatures

There Will Be a Scientific Theory of Deep Learning (arXiv, 2026)

Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs (arXiv, 2026)

InfoNCE Induces Gaussian Distribution (arXiv, 2026)

Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention (arXiv, 2025)