S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
S2PD 提出序列到並行擴散方法,先在高噪聲階段進行自回歸擴散,再於低噪聲階段切換至並行擴散,以提升影片生成對物理規律和符號規則的遵循能力。研究以從頭訓練的像素空間 diffusion transformer,以及透過 LoRA 微調並採用因果注意力改造的預訓練影片模型實作 S2PD。
Published on Oct 5
Authors:
,
Abstract
Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rules. We introduce Serial-to-Parallel Diffusion (S2PD), which performs autoregressive diffusion at high noise before switching to parallel diffusion at low noise. The autoregressive phase provides the serial computation needed to coordinate interdependent events and produce valid state transitions while the parallel phase jointly refines the entire video and reduces sampling time relative to fully serial generation. We implement S2PD with two architectures: a pixel-space diffusion transformer trained from scratch and a pretrained video model adapted through LoRA fine-tuning with causal attention. Across games, physical simulations, and real video, S2PD follows rules more reliably than matched bidirectional baselines and generates videos with greater temporal stability and sampling efficiency than other serial methods.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.06847
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Updated 33 minutes ago • 1jefequien/S2PD
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.06847 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.06847 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co