arXiv Machine Learning October 3, 2026 By Aneesh Barthakur, Mathias Niepert, Luiz F. O. Chamon

Learned End-to-End Guidance Schedules for Diffusion Models

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 17

Integration Matters: Rollout-Based Training for Constrained Diffusion Models

arXiv:2607. 14398v1 Announce Type: cross Abstract: Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution.

By Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg, Frank Wood

diffusion fine-tuning

arXiv Machine Learning

Aug 17

Adversarial Learning of Classifier-Free Guidance Schedules

arXiv:2608. 14038v1 Announce Type: new Abstract: Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment.

By Ashwini Pokle, Alexandre Galashov, Arnaud Doucet, Mauricio Delbracio, Valentin De Bortoli

diffusion benchmarks safety

arXiv AI

3d ago

Image AID via continuous-time reinforcement learning

The paper introduces Amortized Inpainting with Diffusion (AID), a method that keeps a pretrained diffusion backbone fixed and trains a small reusable guidance module offline for image inpainting. AID formulates the problem as deterministic guidance with a supervised terminal objective, derives an auxiliary Gaussian formulation to make it learnable, and proves that solving the randomized problem recovers the optimal deterministic guidance field. Experiments on AFHQv2, FFHQ, and ImageNet show that AID improves the quality–speed trade‑off over strong baselines while adding less than one percent trainable overhead.

By Yilie Huang, Xun Yu Zhou

diffusion reinforcement-learning

arXiv AI

Jun 2

Efficient Weighted Sampling via Score-based Generative Models

arXiv:2502. 04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more.

By Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

diffusion benchmarks

arXiv Computer Vision

Sep 1

EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance

arXiv:2512.17303v3 Announce Type: replace Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free gu...

By Ankit Yadav, Ta Duc Huy, Lingqiao Liu

llms diffusion

Hugging Face Trending Papers

Jun 23

Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization

Diffusion models have achieved strong performance in image, text-to-image, and video generation, where conditional generation is often controlled by classifier-free guidance (CFG). CFG improves condition consistency by increasing a guidance weight, but stronger guidance typically reduces diversity and distributional coverage.

diffusion

One email a morning, machine-written

Related stories

Integration Matters: Rollout-Based Training for Constrained Diffusion Models

Adversarial Learning of Classifier-Free Guidance Schedules

Image AID via continuous-time reinforcement learning

Efficient Weighted Sampling via Score-based Generative Models

EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance

Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization