Scaling a learned flow-matching velocity field $v_\theta$ by a gain $\gamma(t)$ was recently shown to greatly improve generation quality. Prior work argued that velocity fields trained with mean-squared error (MSE) systematically underestimate velocity magnitude and that scaling corrects this error. We show that MSE tr...
Representation Autoencoders (RAEs) generate images from pre-trained visual fea- tures, but their dense token grids make generative modeling expensive. Motivated by local feature correlations, we introduce PoolDINO, a learned affine pooling operator that merges neighboring tokens. Training the pooling operator jointly w...
Ramón Calvo-González, Youssef Saied, François Fleuret· 0 citations
The results suggest that continuous diffusion models can learn nontrivial global constraints, but discrete reasoning tasks require better alignment between training and inference: either through samplers that reduce commitment to early decisions, or through training that teaches the model to correct its own inference-t...
M. Drozdova, S. Nguyen, François Fleuret· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.