arXiv AI July 1, 2026 By Chisato Kumada, Satoru Hiwa, Tomoyuki Hiroyasu

Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Sequence Interpolation

arXiv:2604. 14790v2 Announce Type: replace Abstract: Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such as human preferences and aesthetics, yet it suffers from a fundamental limitation: in high-dimensional generative representations, defining crossover in a semantically consistent manner is difficult, often leading to a mutation-dominated search.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

diffusion

arXiv AI

Jun 2

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

arXiv:2606. 02453v1 Announce Type: cross Abstract: Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse.

By Xiang Li, Dianbo Liu, Kenji Kawaguchi

diffusion

arXiv Machine Learning

Jun 10

Cost-Aware Routing for Efficient Text-To-Image Generation

arXiv:2506. 14753v3 Announce Type: replace-cross Abstract: Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process.

By Qinchan Li, Kenneth Chen, Changyue Su, Wittawat Jitkrittum, Qi Sun, Patsorn Sangkloy

diffusion efficiency

arXiv AI

Jun 4

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

arXiv:2603. 28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt.

By Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or

llms diffusion multimodal safety

arXiv AI

Jul 7

Na\"ive PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation

arXiv:2603. 12506v2 Announce Type: replace-cross Abstract: Text-to-Image (T2I) generation is primarily driven by Diffusion Models (DM) which rely on random Gaussian noise.

By Joong Ho Kim, Nicholas Thai, Souhardya Saha Dip, Dong Lao, Keith G. Mills

diffusion benchmarks

arXiv Machine Learning

Jun 5

Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?

arXiv:2606. 05478v1 Announce Type: cross Abstract: Diffusion Models (DM) have revolutionized text-driven generation by enabling the synthesis of high-quality, photorealistic visual content from user prompts.

By Joong Ho Kim, Keith G. Mills

diffusion

Hugging Face Trending Papers

Jun 29

UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception

Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.

llms diffusion safety

Related stories

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

Cost-Aware Routing for Efficient Text-To-Image Generation

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

Na\"ive PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation

Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?

UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception