The paper introduces a method for specificity‑aware diffusion steering that suppresses undesired samples while preserving desired ones. By formulating the problem as a target‑design task, it derives a time‑dependent target distribution based on overlap between positive and negative reference distributions, and samples from it using a variance‑reduced Sequential Monte Carlo (SMC) sampler. Experiments on synthetic, class‑contrastive, text‑to‑image, and peptide‑MHC tasks demonstrate reduced mode shift, improved sampling stability, and better suppression of undesired regions compared to negative‑guidance baselines.
By Luran Wang, Linrui Ma, Hannes St\"ark, Regina Barzilay
arXiv:2601. 08379v2 Announce Type: replace-cross Abstract: Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data.
By Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia
The paper investigates when to activate classifier‑free guidance (CFG) in diffusion models by treating the diffusion trajectory as a time‑dependent information bottleneck. It shows that the usefulness of conditional information increases after a critical stage defined by a Fisher‑information balance, and proposes a training‑free dynamic CFG strategy that activates guidance based on a stochastic process of score statistics. Experiments across various architectures and tasks confirm that this adaptive rule improves effectiveness, robustness, and general applicability while offering a principled explanation for dynamic guidance.
By Jiayang Gao, Tianyi Zheng, Jiayang Zou, Fengxiang Yang, Luyao Fan, Lv Tang, Bo Li, Jia Wang
arXiv:2610.14136v2 Announce Type: new
Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
By Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe
The paper introduces a data‑free learning objective called relative trajectory balance for training diffusion models to sample from a posterior defined by a diffusion prior and an arbitrary black‑box constraint or likelihood. It proves asymptotic correctness of this objective and demonstrates its use across vision, language, and multimodal tasks, including classifier guidance, language infilling, and text‑to‑image generation. Additionally, the method is applied to continuous control with a score‑based behavior prior, achieving state‑of‑the‑art results in offline reinforcement learning.
By Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Esmeralda S. Whitammer
arXiv:2607. 23226v1 Announce Type: new Abstract: Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped.
By Jinshu Huang, Yiming Jiang, Chunlin Wu
The paper introduces Learned End-to-End Guidance Schedules (LEEGS) for diffusion models, which train a time‑dependent guidance schedule to balance data quality and requirement satisfaction while reducing sampling steps. LEEGS minimizes the guidance function over a small set of examples using stochastic gradient descent and employs a gradient approximation to cut training time by a factor of four. Experiments on tasks such as image inpainting, noisy image inverse problems, face‑ID‑guided generation, and PDE problems show that LEEGS outperforms baselines at the same computational budget or matches constant guidance with only 10% of the steps.
By Aneesh Barthakur, Mathias Niepert, Luiz F. O. Chamon
arXiv:2607. 18516v1 Announce Type: new Abstract: We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $\pi^{sign} = (1+\alpha)\pi^+ - \alpha\pi^-$, where $\alpha>0$, $\pi^+$ is the distribution to promote, and $\pi^-$ is the distribution to suppress.
By Runlong Liao, Baiyu Su, Lizhang Chen, Qiang Liu
arXiv:2606. 04468v1 Announce Type: cross Abstract: Offline multi-objective optimization (Offline MOO) aims to discover novel Pareto-optimal designs based on static datasets without expensive environment interactions.
By Ruiqing Sun, Sen Yang, Dawei Feng, Bo Ding, Yijie Wang, Huaimin Wang
arXiv:2512.17303v3 Announce Type: replace
Abstract: In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free gu...
By Ankit Yadav, Ta Duc Huy, Lingqiao Liu
arXiv:2602. 05533v3 Announce Type: replace Abstract: We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one.
By Zhengyi Guo, Wenpin Tang, Renyuan Xu
arXiv:2610.15699v1 Announce Type: cross
Abstract: Generative modeling for tabular data has advanced to the point where models can synthesize realistic records, recover missing values, and generate sa...
By Jayoung Kim, Sanghyun Hong, Noseong Park