pith. sign in

Proceedings of the AAAI Conference on Artificial Intelligence , author=

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow

cs.CV · 2026-05-07 · unverdicted · novelty 6.0

wAR-Tok adds a Wasserstein-gradient-flow prior-matching term to tokenizer training so that discrete tokens become easier for autoregressive priors to model, cutting AR loss and raising generation FID on CIFAR-10 and ImageNet while keeping reconstruction quality comparable.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow cs.CV · 2026-05-07 · unverdicted · none · ref 74

    wAR-Tok adds a Wasserstein-gradient-flow prior-matching term to tokenizer training so that discrete tokens become easier for autoregressive priors to model, cutting AR loss and raising generation FID on CIFAR-10 and ImageNet while keeping reconstruction quality comparable.