syz
@syz.bsky.social
Reposted by syz
We also introduce two coupling approaches advocated this summer to improve FM training: using either very large sharp Sinkhorn couplings (arxiv.org/abs/2506.05526) or, even better, semidiscrete couplings (arxiv.org/abs/2509.25519), as proposed with Alireza Mousavi-Hosseini and
@syz.bsky.social
@syz.bsky.social
On Fitting Flow Models with Large Sinkhorn Couplings
Flow models transform data gradually from one modality (e.g. noise) onto another (e.g. images). Such models are parameterized by a time-dependent velocity field, trained to fit segments connecting pai...
arxiv.org
November 5, 2025 at 2:04 PM
We also introduce two coupling approaches advocated this summer to improve FM training: using either very large sharp Sinkhorn couplings (arxiv.org/abs/2506.05526) or, even better, semidiscrete couplings (arxiv.org/abs/2509.25519), as proposed with Alireza Mousavi-Hosseini and
@syz.bsky.social
@syz.bsky.social
Reposted by syz
We have been working with Michal Klein on pushing a module to train *flow matching* models using JAX. This is shipped as part of our new release of the OTT-JAX toolbox (github.com/ott-jax/ott)
The tutorial to do so is here: ott-jax.readthedocs.io/tutorials/ne...
The tutorial to do so is here: ott-jax.readthedocs.io/tutorials/ne...
November 5, 2025 at 2:04 PM
We have been working with Michal Klein on pushing a module to train *flow matching* models using JAX. This is shipped as part of our new release of the OTT-JAX toolbox (github.com/ott-jax/ott)
The tutorial to do so is here: ott-jax.readthedocs.io/tutorials/ne...
The tutorial to do so is here: ott-jax.readthedocs.io/tutorials/ne...
Reposted by syz
Wow! Finally OT done on the entire training set to train a diffusion model!
Our two phenomenal interns, Alireza Mousavi-Hosseini and Stephen Zhang @syz.bsky.social have been cooking some really cool work with Michal Klein and me over the summer.
Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching
🧵
Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching
🧵
October 4, 2025 at 7:03 AM
Wow! Finally OT done on the entire training set to train a diffusion model!
Reposted by syz
Our two phenomenal interns, Alireza Mousavi-Hosseini and Stephen Zhang @syz.bsky.social have been cooking some really cool work with Michal Klein and me over the summer.
Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching
🧵
Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching
🧵
October 3, 2025 at 8:50 PM
Our two phenomenal interns, Alireza Mousavi-Hosseini and Stephen Zhang @syz.bsky.social have been cooking some really cool work with Michal Klein and me over the summer.
Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching
🧵
Relying on optimal transport couplings (to pick noise and data pairs) should, in principle, be helpful to guide flow matching
🧵
Reposted by syz
Alireza Mousavi-Hosseini, Stephen Y. Zhang, Michal Klein, Marco Cuturi: Flow Matching with Semidiscrete Couplings https://arxiv.org/abs/2509.25519 https://arxiv.org/pdf/2509.25519 https://arxiv.org/html/2509.25519
October 1, 2025 at 6:33 AM
Alireza Mousavi-Hosseini, Stephen Y. Zhang, Michal Klein, Marco Cuturi: Flow Matching with Semidiscrete Couplings https://arxiv.org/abs/2509.25519 https://arxiv.org/pdf/2509.25519 https://arxiv.org/html/2509.25519