← Back to all news
arXiv Machine Learning By Jiayang Gao, Tianyi Zheng, Jiayang Zou, Fengxiang Yang, Luyao Fan, Lv Tang, Bo Li, Jia Wang

Opening the Black Box of Classifier-Free Guidance via Information Bottleneck

Read the original on arXiv Machine Learning →

The paper investigates when to activate classifier‑free guidance (CFG) in diffusion models by treating the diffusion trajectory as a time‑dependent information bottleneck. It shows that the usefulness of conditional information increases after a critical stage defined by a Fisher‑information balance, and proposes a training‑free dynamic CFG strategy that activates guidance based on a stochastic process of score statistics. Experiments across various architectures and tasks confirm that this adaptive rule improves effectiveness, robustness, and general applicability while offering a principled explanation for dynamic guidance.

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.

Related stories

Hugging Face Trending Papers
Jul 22

Analytic Distribution of Classifier-Free Guidance for Schedule Design

Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^ωq_0^{1-ω}$. We analyze CFG through the probability flow ODE and derive exact analytic path-integral representations of the induced distributions for both constant and time-dependent guidance.

diffusion
More like this →
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.

By Aneesh Barthakur, Mathias Niepert, Luiz F. O. Chamon
diffusiondata-engineering
More like this →