aiqbench analysis
The article introduces Normalizing Trajectory Models (NTM), a novel architecture that applies conditional normalizing flows to diffusion sampling trajectories to recover exact likelihoods in few-step generation. By retaining the likelihood framework often lost in distillation or adversarial approaches, NTM achieves high-quality image synthesis in just four steps while enabling self-distillation from pretrained flow-matching models. This work advances the theoretical and practical limits of generative modeling by addressing the bottleneck of coarse transitions without sacrificing probabilistic guarantees.
Normalizing Trajectory Models
Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training. Architecturally, NTM combines shallow invertible blocks within each step with a deep parallel…
Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training. Architecturally, NTM combines shallow invertible blocks within each step with a deep parallel predictor across the trajectory, forming an end-to-end network trainable from scratch or initializable from pretrained flow-matching models. Its exact trajectory likelihood further enables self-distillation: a lightweight denoiser trained on the score function induced by the model itself produces high-quality samples in four steps. On text-to-image benchmarks, NTM matches or outperforms strong image generation baselines in just four sampling steps while uniquely retaining exact likelihood over the generative trajectory.
Related readings and updates.
Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a few steps. When the student underperforms, the usual explanation is insufficient capacity. We argue the opposite: the trajectory is the bottleneck, not the student. Each training trajectory is built through a…
Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks, making them viable alternatives to other methods such as diffusion models. In this work, we further advance the state of Normalizing Flow generative models by introducing iterative TARFlow (iTARFlow). Unlike…
Full text under the publisher's open licence · 280 words
Related coverage
Deep recurrent models are less robustly CoT-monitorable than normal CoT models in a toy setting
LessWrong · Sep 18, 2026
When Partial Credit Opposes Completion
Snorkel AI Blog · Oct 15, 2026
EditWM: Event-Decomposed World Modeling with Incremental Correction for End-to-End Autonomous Driving
arXiv · Sep 22, 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026