← Back to all news
arXiv AI By Jinho Chang, Jong Chul Ye

Manifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment

Read the original on arXiv AI →

The paper introduces ZeNOVA, a gradient‑free method for aligning initial noise in generative models. It uses annealed soft‑value guidance, manifold‑constrained hyperspherical Langevin dynamics, and Metropolis‑Hastings jumps to address instability in black‑box reward settings. Experiments on image and video models show ZeNOVA outperforms existing zeroth‑order baselines by more stably optimizing noise toward higher rewards.

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 AI.

Related stories

arXiv Machine Learning
Sep 17

Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows

The paper introduces Contrastive Noise Alignment (CNA), a training-time method for generative flow models that dynamically aligns Gaussian noise with data samples using a cross-modal InfoNCE objective. By modeling noise as an interacting particle system and regularizing with angular entropy and radial norm penalties, CNA reduces arbitrary data-noise couplings and flow curvature. Empirical results show that CNA improves generation quality, lowering FID by over 50% for few-step pixel-space generation compared to standard rectified flow and outperforming optimal transport baselines by at least 24%.

By Lennart Wittke, Vinicius Azevedo
diffusionmultimodalsafety
More like this →
arXiv Computer Vision
Sep 7

Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching

The paper introduces DM-Align, a single-stage optimization framework that jointly performs distribution matching for distillation and aligns video generative models with human preferences. By deriving complementary gradient directions—one minimizing the gap between real and fake models and another guiding the model toward preferred samples—the method eliminates the need for separate reinforcement learning and distillation stages. Experiments on multiple foundational video models show that this sample-guided approach consistently outperforms both standalone variants and traditional two-stage pipelines.

By Jiuzhou Lin, Junlong Wu, Fei Zuo, Huan Ouyang, Dewen Fan, Boheng Zhang, Huaiqing Wang, Jia Sun, Fan Yang, Houde Liu, Kehai Chen, Min Zhang, Tingting Gao, Han Li
diffusionreinforcement-learningefficiencysafety
More like this →