pith. sign in

This limitation may be attributed to our reliance on extensive web datasets, such as LAION and DataComp

While NOV A outperforms most models of comparable size, matches the overall score of state-of-the-art models, we observe that increasing the model scale results in marginal improvements, does not boost the text rendering performance · 2023

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

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2024 1

verdicts

UNVERDICTED 1

representative citing papers

Autoregressive Video Generation without Vector Quantization

cs.CV · 2024-12-18 · unverdicted · novelty 6.0

NOVA reformulates video generation as non-quantized autoregressive frame-by-frame temporal prediction combined with set-by-set spatial prediction, outperforming prior AR video models and some diffusion models in efficiency and quality.

citing papers explorer

Showing 1 of 1 citing paper.

  • Autoregressive Video Generation without Vector Quantization cs.CV · 2024-12-18 · unverdicted · none · ref 35

    NOVA reformulates video generation as non-quantized autoregressive frame-by-frame temporal prediction combined with set-by-set spatial prediction, outperforming prior AR video models and some diffusion models in efficiency and quality.