arXiv Machine Learning
Co-Evolving Paths and Flows via Path-Flow Alignment
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Oct 6
Co-Evolving Paths and Flows via Path-Flow Alignment
We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity field, we jointly train an endpoint-preserving p...
arXiv AI
Jul 15
Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models
arXiv:2607. 12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising.
arXiv Computer Vision
Oct 2
Smoother Flow Matching via Contrastive Trajectory Repulsion
arXiv:2610.01408v1 Announce Type: new Abstract: Trajectory crossing remains a critical bottleneck in Flow Matching (FM), and previous works typically view these crossings from a theoretical optimizat...
arXiv AI
Sep 30
Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas th...
arXiv Machine Learning
Sep 3
CAT-Flow: Curvature-Adaptive sTeps for Flow Matching
The paper introduces CAT-Flow, a pair of lightweight, training‑free algorithms—CAT‑OV and CAT‑OT—that adapt step‑sizes during Flow Matching inference by estimating curvature in time or state space. These methods avoid extra neural evaluations and achieve constant‑order truncation error bounds. Experiments show that CAT‑OV and CAT‑OT improve image quality metrics across four text‑to‑image Flow Matching models, cutting the required generation steps by up to 40%.
arXiv Machine Learning
Sep 11
Prediction--Loss Alignment for Sampler--Robust Flow Matching Training
The paper examines the common practice in diffusion and flow matching of predicting the clean signal, converting it to a velocity, and training with a velocity-space loss. It shows that this conversion can cause unstable optimization due to singular endpoint amplification, but that prediction–loss alignment removes this source of non‑integrability and ensures a finite second moment for all timesteps, even with uniform sampling. Experiments confirm that aligned objectives remain trainable across different samplers, reconciling theoretical concerns with empirical success.