arXiv AI July 9, 2026 By Jinho Chang, Changsun Lee, Hyungjin Chung, Jong Chul Ye

ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts

arXiv:2411. 17077v2 Announce Type: replace-cross Abstract: As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term as a Negative Prompting (NP) to filter out unwanted features from samples.

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 AI.

arXiv AI

Jun 10

MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance

arXiv:2601. 08379v2 Announce Type: replace-cross Abstract: Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data.

By Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia

diffusion fine-tuning benchmarks safety

arXiv AI

Jun 12

The Safety-Aware Denoiser for Text Diffusion Models

arXiv:2605. 08116v2 Announce Type: replace-cross Abstract: Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored.

By Amman Yusuf, Zhejun Jiang, Mijung Park

diffusion safety

arXiv Machine Learning

Jun 25

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

arXiv:2507. 09052v3 Announce Type: replace-cross Abstract: Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes.

By Fang Chen, Alex Villa, Gongbo Liang, Fuxing Li, Xiaoyi Lu, Meng Tang

llms diffusion safety

arXiv AI

Jun 2

IDLM: Inverse-distilled Diffusion Language Models

arXiv:2602. 19066v2 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) have recently achieved strong results in text generation.

By David Li, Nikita Gushchin, Dmitry Abulkhanov, Eric Moulines, Ivan Oseledets, Maxim Panov, Alexander Korotin

llms diffusion efficiency

arXiv Computer Vision

Aug 21

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

arXiv:2608. 19504v1 Announce Type: new Abstract: We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition.

By Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd, Vinay P. Namboodiri

diffusion

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

One email a morning, machine-written

Related stories

MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance

The Safety-Aware Denoiser for Text Diffusion Models

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

IDLM: Inverse-distilled Diffusion Language Models

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

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