← Back to all news
arXiv Machine Learning By Zhangyong Liang, Ying Huang, Haibin Ling

One-Step Generative Modeling via Training Dynamics Action

Read the original on arXiv Machine Learning →

The paper introduces TDAction, a method for one‑step generative modeling that selects transport targets during training based on a cost reflecting shared‑parameter effort and terminal mismatch. By formulating this as a soft‑terminal control problem, the authors derive a closed‑form Batch Tangent Action‑to‑Go value that captures cross‑sample interactions and can be efficiently implemented with randomized tangent probes. Experiments on ImageNet 256×256 demonstrate that TDAction achieves an FID below 1.1 without distillation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 17

Friction-Augmented Drifting Models for Resource-Efficient Domain Translation

arXiv:2604. 18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern when compute is limited.

By Arkadii Kazanskii, Tatiana Petrova, Andrey Ustyuzhanin, Konstantin Bagrianskii, Aleksandr Puzikov, Radu State
diffusion
More like this →
arXiv AI
Sep 15

Freeze, Share, Shrink: Rethinking the Action Backbone in Diffusion Policies

The paper argues that diffusion-based action policies can use a frozen, observation‑free backbone as a reusable trajectory prior, with task adaptation handled entirely by the conditioning pathway. By pretraining a general action head on forward‑kinematics data and then freezing it, the authors show that a single backbone can match or outperform normally trained models on MimicGen and LIBERO. Their experiments reveal that a small 5 M‑parameter MLP backbone can rival large U‑Net and transformer backbones, indicating that action backbones are often over‑parameterized and that image‑style architectures may not be the best fit for low‑dimensional action generation.

By Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU
llmsdiffusionroboticsmultimodalbenchmarkssafety
More like this →