We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to handle the joint distribution of multiple modalities. It outperforms previous any-to-any models on a wide range of tasks, such as text-to-image and text-to-audio synthesis. Our work offers three key contributions: First, we extend RF to a multi-modal setting and introduce a novel guidance mechanism, enabling users to flexibly control the alignment between different modalities in the generated outputs. Second, we propose a novel architecture that extends the text-to-image MMDiT architecture of Stable Diffusion 3 and enables audio and text generation. The extended modules can be efficiently pretrained individually and merged with the vanilla text-to-image MMDiT for fine-tuning. Lastly, we conduct a comprehensive study of the design choices of rectified flow transformers for large-scale audio and text generation, providing valuable insights into optimizing performance across various modalities. Code is available at https://github.com/jacklishufan/OmniFlows.

We analyze the impact of group activities targeting Social-Emotional Learning (SEL) and peer effects on the risk and protective factors associated with gang involvement among youth participating in the Los Angeles Mayor’s Office of Gang Reduction and Youth Development (GRYD) Prevention program. We compare the impact of targeted and non-targeted activities in decreasing Internal Risk, External Risk, and Family Norms Risk, as measured by a standardized questionnaire. We show that targeted activities are effective in decreasing Internal Risk and that activities focusing on Emotional Management are the most beneficial. Since targeted activities involve group interactions, we investigate the impact of peer network effects on outcomes using both a linear-in-means model and dynamic mode decomposition with control (DMDc). Our analysis suggests that peer network effects contribute to beneficial changes in risk and protective factors above and beyond the skill-building content of the activities.