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.
By Jinho Chang, Jong Chul Ye
arXiv:2606. 02453v1 Announce Type: cross Abstract: Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse.
By Xiang Li, Dianbo Liu, Kenji Kawaguchi
arXiv:2608.29647v1 Announce Type: new
Abstract: To mitigate the time complexity of generative models, one-step generative models have recently emerged through direct mapping from noise to data in a s...
By Hoseong Hwang, Woorim Han, Joungin Chun, Jinseong Park, Jaewoong Choi
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
arXiv:2603. 14504v2 Announce Type: replace-cross Abstract: Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at inference time.
By Niklas Schweiger, Daniel Cremers, Karnik Ram
arXiv:2601. 14430v2 Announce Type: replace-cross Abstract: Controlling generative models is computationally expensive.
By Peter Potaptchik, Adhi Saravanan, Abbas Mammadov, Alvaro Prat, Michael S. Albergo, Yee Whye Teh
arXiv:2606. 18066v1 Announce Type: new Abstract: We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel unchanged and requiring only a single sample per step.
By Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen, Minhyuk Sung
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
We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency.
arXiv:2602.19600v2 Announce Type: replace
Abstract: Many high-dimensional datasets concentrate near a low-dimensional structure embedded in the ambient space. Generative models for such data must con...
By Xinyu Tian, Xiaotong Shen
arXiv:2607. 09133v1 Announce Type: cross Abstract: While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs severe inference latency.
By Yiting Wang, Jingyi Zhang, Wenhu Zhang, Ke Chao, Yves Liang, Kun Cheng, Kang Zhao
The paper proposes a continuous‑time generative framework that models time‑dependent data as evolution on a learned data manifold. By using pretrained score‑based models as geometric priors, it learns a vector field that drives data along score‑induced interpolation paths, enabling generation at arbitrary timestamps and temporal super‑resolution. The method includes a regression‑based training objective, a stability‑promoting term interpreted as denoising score matching, and a probabilistic extension for future trajectory distributions, demonstrated on natural video, PDE‑based fields, and molecular dynamics.
By Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov, Andreas Dengel, Andrew B. Duncan, Sebastian J. Vollmer