The paper argues that the concrete random noise used in diffusion models is not merely a passive perturbation but a learnable input that can be exploited by the model. By analyzing how clean data and realized noise jointly form the noisy input, the authors show that the model can learn regularities in the data or in the noise structure, and that these two routes can interact. Experiments on MNIST and CIFAR‑10 using pseudorandom streams demonstrate that structured‑noise training can reduce prediction loss, but this advantage disappears when test noise is replaced with IID noise, indicating that the learned dependence is tied to the specific noise structure.
By Shengzhi Deng, Chenqi Ye, Yanze Guo
arXiv:2607. 20540v1 Announce Type: cross Abstract: How should a diffusion model decide which noise levels to train on, and how much?
By Luca Ambrogioni, Giulio Franzese, Alberto Foresti, Gabriel Raya, Bac Nguyen, Georgios Batzolis, Yuhta Takida, Naoki Murata, Chieh-Hsin Lai, Yuki Mitsufuji
arXiv:2607. 12360v1 Announce Type: new Abstract: The cooldown phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining, lowers the final training loss in some settings and does nothing in others.
By Subham Singh, Ashutosh Mishra, Subha Raut
arXiv:2512. 19311v2 Announce Type: replace-cross Abstract: This paper studies the training-testing discrepancy (a.
By Hui Li, Fu-Yun Wang, Haoyuan Xia, Jiayue Lyu, Kaihui Cheng, Siyu Zhu, Jingdong Wang
arXiv:2310. 05264v5 Announce Type: replace Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs.
By Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu
arXiv:2601. 04539v2 Announce Type: replace-cross Abstract: In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biological variability and regularize learning.
By Noah Eckstein, Manoj Srinivasan
arXiv:2609.16788v1 Announce Type: new
Abstract: Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectur...
By Dingyan Shang, Zhenyu Xu, Youting Wang, Bonan Shen, Bowen Liu
Uniform discrete diffusion models (UDMs) typically rely on explicit time conditioning, yet this study finds that such conditioning is often unnecessary in practice. While the population‑optimal UDM predictor generally depends on time—controlling how much the model should trust the observed context—the dependence becomes negligible in finite‑data language settings. Empirical results show that trained language UDMs exhibit limited time sensitivity across most of the diffusion trajectory, and time‑agnostic predictors can match or outperform time‑conditioned models on various datasets and training objectives.
By Chunsan Hong, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Jong Chul Ye, Yuki Mitsufuji
arXiv:2606. 27696v1 Announce Type: cross Abstract: In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models.
By Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang
The paper studies how to allocate a fixed computational budget across the denoising steps of diffusion models to improve sample quality at deployment. It shows that the expected benefit of evaluating multiple candidates at a step can be decomposed into a step‑specific sensitivity and a universal sample‑size factor, and that the optimal allocation follows a water‑filling structure. Experiments demonstrate that this allocation achieves the same quality as a uniform strategy while reducing function evaluations by 20–50%.
By Yuan Cao, Yifu Tang, Hangqi Li, Zeyu Zheng
arXiv:2607.02137v3 Announce Type: replace-cross
Abstract: We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Unifo...
By Yilie Huang, Wenpin Tang, Xun Yu Zhou
The paper introduces the first controlled benchmark for optimizers in discrete diffusion models, evaluating seven optimizers (AdamW, Lion, Muon, SOAP, MARS, MARS‑M, Schedule‑Free) across four diffusion formulations: masked diffusion on text8, uniform diffusion on QM9 and LM1B, and Gaussian diffusion on CelebA‑64. Each optimizer undergoes the same search protocol and is retrained with full budget and multiple seeds, revealing that AdamW, while strong, is not universally optimal and that optimizers validated on autoregressive language models (Muon, MARS‑M, SOAP) can outperform tuned AdamW on certain tasks.
By Arman Bolatov, Egor Shulgin, David Li, Abduragim Shtanchaev, Sebastian U. Stich, Maxim Panov, Eric Moulines, Peter Richt\'arik, Martin Tak\'a\v{c}