pith. sign in

Title resolution pending

Stage 1 (Video data) Stage 2 (3D data) Stage 3 (3D data) Stage 4 (3D data) [256×256] [256×256] [512×512] [1024mixed AR] Batch Size # Steps Batch Size # Steps Batch Size # Steps Batch Size # Steps Kaleido-Small1024 700K 1024 300K 256 100K 25 · 2048

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

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Scaling Sequence-to-Sequence Generative Neural Rendering

cs.CV · 2025-10-05 · unverdicted · novelty 6.0

Kaleido is a masked autoregressive generative model that unifies 3D view synthesis and video modeling by pre-training a single transformer on video data, achieving SOTA zero-shot and many-view performance on view synthesis benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Scaling Sequence-to-Sequence Generative Neural Rendering cs.CV · 2025-10-05 · unverdicted · none · ref 16

    Kaleido is a masked autoregressive generative model that unifies 3D view synthesis and video modeling by pre-training a single transformer on video data, achieving SOTA zero-shot and many-view performance on view synthesis benchmarks.