arXiv AI
SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 15
Correction Training for Diffusion Models
arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
arXiv Machine Learning
Oct 3
Learned End-to-End Guidance Schedules for Diffusion Models
The paper introduces Learned End-to-End Guidance Schedules (LEEGS) for diffusion models, which train a time‑dependent guidance schedule to balance data quality and requirement satisfaction while reducing sampling steps. LEEGS minimizes the guidance function over a small set of examples using stochastic gradient descent and employs a gradient approximation to cut training time by a factor of four. Experiments on tasks such as image inpainting, noisy image inverse problems, face‑ID‑guided generation, and PDE problems show that LEEGS outperforms baselines at the same computational budget or matches constant guidance with only 10% of the steps.
arXiv AI
Sep 30
On Trajectory-Aware Training for Masked Diffusion Language Models
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
arXiv Machine Learning
Oct 21
StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion
arXiv:2605.15816v2 Announce Type: replace-cross Abstract: Stipple patterns, point sets whose local density tracks a target image, are traditionally produced by per-density iterative optimizers, which...
arXiv AI
Oct 21
TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling
arXiv:2610.26025v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) deliver high-fidelity image and video generation, but inference requires many sequential model evaluations. Two...
arXiv Computation and Language
1d ago
Self-Regularized Flow Language Models
arXiv:2610.37115v1 Announce Type: cross Abstract: We introduce SERF (Self-Regularized Flow Language Models), a simple self-supervised framework for improving continuous diffusion language models by e...