arXiv AI
TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 25
Accelerating Video Diffusion via Training-Free Trajectory Routing
The paper introduces TRACK, a training‑free trajectory routing method that accelerates video diffusion by selectively switching between large and small models during denoising steps. A calibration process generates a disagreement score map, guiding the selection of the appropriate model at each step to maintain quality while reducing computational cost. Experiments on Wan 2.1, Cosmos 3, TurboDiffusion, and FastVideo show speedups ranging from 1.95× to 2.73× with comparable quality and diversity.
Hugging Face Trending Papers
Sep 24
Accelerating Video Diffusion via Training-Free Trajectory Routing
Accelerating Video Diffusion via Training-Free Trajectory Routing (TRACK) introduces a heterogeneous denoising strategy that switches between large and small diffusion models at selected steps, determined by a calibration process that measures disagreement between model predictions. By routing quality-sensitive steps to the large model and low-disagreement steps to the small model, TRACK achieves significant speedups—up to 2.73×—across several video diffusion benchmarks while maintaining comparable quality and diversity. The method requires no retraining, architectural changes, or online dual-model evaluation, making it a practical acceleration paradigm for video diffusion.
Hugging Face Trending Papers
Oct 6
Consistent Distribution Matching for Data-Free Diffusion Distillation
Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to learn from a teacher's dynamic...
arXiv Machine Learning
Oct 8
Consistent Distribution Matching for Data-Free Diffusion Distillation
Consistent Distribution Matching is a data‑free distillation technique that accelerates diffusion and flow models by unifying sample generation and score estimation in a single student network. The method requires only a frozen teacher and a trainable student, optimizing a single objective that provably leads to Wasserstein convergence of the student’s flow‑map to the teacher’s marginals. On ImageNet 256×256, it achieves an FID of 2.04 with one function evaluation and 1.37 with four evaluations after just 40 training epochs, outperforming existing data‑free baselines.
arXiv Computer Vision
Oct 15
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
arXiv:2610.20220v1 Announce Type: new Abstract: Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a b...
arXiv Computer Vision
Oct 15
RepForcing: Representation-Space Initialization for Autoregressive Video Distillation
arXiv:2610.20111v1 Announce Type: new Abstract: Distilling pretrained video diffusion models into few-step autoregressive (AR) generators typically combines student initialization with distribution m...