arXiv AI
Jul 1
Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
arXiv:2510. 17917v2 Announce Type: replace-cross Abstract: Data unlearning aims to remove the influence of specific training samples from a trained model.
The Emergence of Reproducibility and Generalizability in Diffusion Models
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.
Related stories
arXiv Machine Learning
Aug 4
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
arXiv:2608. 02575v1 Announce Type: new Abstract: Diffusion models rely on stochastic inputs, yet on finite-precision hardware, the "randomness" they consume is realized as deterministic numerical orbits generated by pseudorandom rules.
arXiv Machine Learning
Jun 9
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
arXiv:2606. 09718v1 Announce Type: new Abstract: Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored.
arXiv AI
Jul 7
A Random Matrix Theory Perspective on the Consistency of Diffusion Models
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.
arXiv AI
Jun 4
Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity
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.
Hugging Face Trending Papers
Jul 9
An exact information theory of generalization phase transitions in Bayesian diffusion models
How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information restricted diffusion (BIRD) models, in which each pixel observes restricted information about noisy data.
arXiv Machine Learning
Jul 10
An exact information theory of generalization phase transitions in Bayesian diffusion models
arXiv:2607. 08041v1 Announce Type: new Abstract: How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery.
arXiv Machine Learning
Jul 7
Benign Overfitting Does Not Occur in Diffusion Models
arXiv:2607. 02671v1 Announce Type: cross Abstract: Benign overfitting and double descent have come to shape our understanding of generalization in deep learning, establishing that overfitting is not only compatible with good generalization but can actively benefit it.
arXiv AI
Jun 2
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
arXiv:2604. 05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation.
arXiv AI
Jun 8
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
arXiv:2606. 06712v1 Announce Type: cross Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs).
arXiv Machine Learning
Jun 15
Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves
arXiv:2502. 00336v3 Announce Type: replace Abstract: We theoretically investigate the phenomena of generalization and memorization in diffusion models.
arXiv Machine Learning
Jul 28
Learning Sampling Parameters for Diffusion Models
arXiv:2607. 23488v1 Announce Type: new Abstract: Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules.