pith. sign in

Autoregressive image generation with masked bit modeling

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

representative citing papers

Representation Fr\'echet Loss for Visual Generation

cs.CV · 2026-04-30 · unverdicted · novelty 8.0

Fréchet Distance optimized as FD-loss in representation space by decoupling population size from batch size improves generator quality, enables one-step generation from multi-step models, and motivates a multi-representation metric FDr^k.

citing papers explorer

Showing 2 of 2 citing papers.

  • Representation Fr\'echet Loss for Visual Generation cs.CV · 2026-04-30 · unverdicted · none · ref 57

    Fréchet Distance optimized as FD-loss in representation space by decoupling population size from batch size improves generator quality, enables one-step generation from multi-step models, and motivates a multi-representation metric FDr^k.

  • A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens cs.CV · 2026-04-06 · conditional · none · ref 87

    Delta tokens compress VFM feature differences into single tokens, enabling a lightweight generative world model that predicts diverse futures with far lower compute than existing approaches.