#normalizing-flows

The latest AI and developer news about #normalizing-flows, with the original source and a short summary.

Apple Researchers Introduce Normalizing Trajectory Models for Exact-Likelihood Few-Step Generation

Apple researchers introduced Normalizing Trajectory Models (NTM), a framework that matches strong baselines in four sampling steps while retaining exact likelihood over the generative trajectory.

·3·2026.10.08 09:00

STARFlow2 Achieves Unified Multimodal Generation by Connecting Language Models and Normalizing Flows

Apple released STARFlow2, which combines LLMs and normalizing flows to generate text and images in a unified manner.

·1·2026.08.25 09:00

Trajectory Models for Few-Step Diffusion

NTM aims for both 4-step generation and exact likelihood by training the reverse step as a normalizing flow.

·1·2026.05.12 09:00

Normalizing Flows Combined with Iterative Denoising

Apple researchers proposed iTARFlow, showing competitive results on ImageNet 64, 128, and 256.

·1·2026.05.06 09:00

STARFlow-V: End-to-End Video Generation Modeling Based on Normalizing Flows

STARFlow-V demonstrates high-quality autoregressive video generation without diffusion.

·2026.04.30 09:00