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:2605.08144v2 Announce Type: replace-cross
Abstract: Training a diffusion model involves two sources of randomness for each data sample: the timestep and the Gaussian noise realization. The time...
By Haokai Zhao, Da Xing, Hanqun Cao, Tinson Xu, Xinyu Xiang, Yanchao Li, Xiangru Tang, Hongbin Lin, Zehong Wang, Kuan Pang, Peng Xia, Molei Tao, Li Erran Li, Aditya Joshi, Jure Leskovec, Fang Wu
arXiv:2601. 22450v2 Announce Type: replace-cross Abstract: Masked Diffusion Language Models have recently emerged as a powerful generative paradigm, yet their generalization properties remain understudied compared to their auto-regressive counterparts.
By Jianhao Huang, Baharan Mirzasoleiman
arXiv:2606. 13796v1 Announce Type: cross Abstract: Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution.
By Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan
arXiv:2605.12597v3 Announce Type: replace-cross
Abstract: Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently ena...
By Luca Maria Del Bono, Giulio Biroli, Patrick Charbonneau, Marylou Gabri\'e
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: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:2506. 00849v2 Announce Type: replace Abstract: Despite the empirical success of Diffusion Models (DMs) and Variational Autoencoders (VAEs), their generalization performance remains theoretically underexplored, especially lacking a full consideration of the shared encoder-generator structure.
By Qi Chen, Jierui Zhu, Florian Shkurti
arXiv:2602. 02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed.
By Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan
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:2602.12624v2 Announce Type: replace
Abstract: Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by h...
By Sangwoo Jo, Sungjoon Choi
arXiv:2609.37974v1 Announce Type: cross
Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
By Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis B\'ethune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, Jo\~ao Monteiro