Skip to content
mlvlabPublic

About

Official repository of "Learning to Solve Generative ODEs Beyond the Linear Span" (NeurIPS 2026)

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

Learning to Solve Generative ODEs Beyond the Linear Span

NeurIPS 2026

Sihyeon Kim1   Seunghun Lee2   Vikas Singh3,§   Hyunwoo J. Kim2,§

1Korea University    2KAIST    3University of Wisconsin-Madison

SpanLift overview

Few-step ODE solvers for diffusion and flow models, whether analytic (iPNDM, DPM-Solver++) or learned (DyWeight, S4S), build each step as a scalar-weighted combination of buffered velocities, so the update can never leave the linear span of the velocity buffer. SpanLift keeps a fixed base solver as an in-span prior and adds a lightweight spatial residual operator over the state and velocity buffer that corrects the update beyond this span. It is trained by endpoint teacher matching, keeps the pretrained backbone frozen, and adds no extra model NFEs. With only 3 NFE, SpanLift improves FID from 8.16 to 5.69 on CIFAR-10 and from 17.37 to 11.83 on ImageNet 64×64.

Code

🚧 Coming soon.

Citation

@inproceedings{kim2026spanlift,
  title     = {Learning to Solve Generative {ODEs} Beyond the Linear Span},
  author    = {Kim, Sihyeon and Lee, Seunghun and Singh, Vikas and Kim, Hyunwoo J.},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2026}
}

About

Official repository of "Learning to Solve Generative ODEs Beyond the Linear Span" (NeurIPS 2026)

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors