A 16B causal autoregressive diffusion system reports real-time 720p video editing at about 30 FPS on one B200 GPU, beating streaming editors and matching several offline systems in benchmark scores.
Diffusion forcing: Next-token prediction meets full-sequence diffusion.Advances in Neural Information Processing Systems, 37:24081–24125, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
A 16B causal autoregressive diffusion system reports real-time 720p video editing at about 30 FPS on one B200 GPU, beating streaming editors and matching several offline systems in benchmark scores.