arXiv:2606. 29287v1 Announce Type: new Abstract: Diffusion and continuous-flow generative models achieve high-quality generation, and their deterministic sampling can be formulated as solving learned ODE dynamics.
By Chen Wang, Peiran Yun, Pan Xie, Ke Deng
arXiv:2609.36324v1 Announce Type: cross
Abstract: Flow-matching text-to-speech (TTS) models achieve high synthesis quality but require many neural function evaluations (NFEs) to integrate their gener...
By Yentl Collin, Evan Dufraisse, Amr Mohamed, Amine Khelif Khelif, Dani Bouch, Guokan Shang
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...
The paper introduces Trajectory-Regularized Distribution Distillation (TRD), a method that merges distribution-level and trajectory-level supervision for one-step generative models. TRD uses a momentum-mixture policy derived from a single student forward pass, eliminating the need for an extra network to estimate the student’s score. Experiments on SANA-1.6B and Stable Diffusion 3.5 demonstrate that TRD surpasses existing consistency and distribution matching baselines in generation quality and training efficiency, though it slightly reduces sample diversity.
By An Zhao, Yixiang Zhou, Zejian Li, Yi Guo, Pei Chen, Lingyun Sun
The paper introduces TACD, a Terminal‑Amplification‑Controlled Distillation method that trains efficient text‑to‑motion generators using on‑policy flow distillation from pretrained teachers, without requiring real‑motion data. TACD addresses a failure mode where velocity matching over‑weights errors near the denoising endpoint by tying the latest teacher query to the student’s step size, thereby bounding loss weights in clean‑motion space. Experiments on HumanML3D, KIT‑ML, HY‑Motion, and Kimodo show that TACD improves few‑step generation quality, reduces FID scores, and achieves significant speedups and memory savings compared to teacher models.
By Wei-Jin Huang, Yuan-Ming Li, Kun-Yu Lin, Wang Luo, Yinlin Zhu, Yue Yu, Shenghao Ye, Junbin Yuan, Fa-Ting Hong, Qing Zhang, Wei-Shi Zheng
Few-step flow-map generators, including MeanFlow and consistency models, enable efficient sampling through long-range transport, yet their on-policy distillation remains underexplored. We introduce Fl...
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.
By Yuxiang Fu, Qi Yan, Zike Wu, Yongxing Zhang, Purang Abolmaesumi, Lele Wang, Renjie Liao
arXiv:2607. 14947v1 Announce Type: cross Abstract: Modern generative models are increasingly trained using model-generated signals, creating both opportunities for self-improvement and risks of collapse.
By Saptarshi Roy, Debepsita Mukherjee, Pratik Patil
arXiv:2609.37851v1 Announce Type: cross
Abstract: Few-step flow-map generators, including MeanFlow and consistency models, enable efficient sampling through long-range transport, yet their on-policy...
By Zhiqi Li, Bo Zhu
arXiv:2610.27146v1 Announce Type: new
Abstract: Few-step trajectory distillation aims to learn accurate global updates from dense local supervision along a teacher's sampling trajectory. Existing app...
By Hongyi Fang, Benjia Zhou
The paper introduces Velocity Adversarial Distillation (VAD), a method that uses a learned critic to compare velocity fields of student and teacher diffusion models, turning disagreements into learning signals. VAD unifies several existing distillation techniques and leads to VA‑TDM, which applies trajectory distribution matching and transition‑aware online velocity learning to supervise partial denoising along the student’s sampling path. Experiments demonstrate that VA‑TDM achieves state‑of‑the‑art performance for four‑step text‑to‑image and text‑to‑video generation, outperforming prior few‑step methods and approaching the quality of many‑step baselines.
By Yihong Luo, Tianyu Pang, Tianyang Hu
Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a bidirectional diffusion model into a causal few-st...