Alex Lambert
@allambert.bsky.social
Machine Learning researcher working on kernels and duality. Broad interest in machine learning and applications.
Reposted by Alex Lambert
New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719
🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*?
w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇
🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*?
w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇
June 18, 2025 at 8:08 AM
New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719
🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*?
w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇
🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*?
w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇
Reposted by Alex Lambert
New blog post: the Hutchinson trace estimator, or how to evaluate divergence/Jacobian trace cheaply. Fundamental for Continuous Normalizing Flows
mathurinm.github.io/hutchinson/
mathurinm.github.io/hutchinson/
November 21, 2024 at 8:48 AM
New blog post: the Hutchinson trace estimator, or how to evaluate divergence/Jacobian trace cheaply. Fundamental for Continuous Normalizing Flows
mathurinm.github.io/hutchinson/
mathurinm.github.io/hutchinson/