Fetching the paper…
Reading the bibliography…
We develop theory to understand an intriguing property of diffusion models for image generation that we term critical windows.
Asymptotic methods in statistical decision theory
LeCam, L · 1986
Earlier work this paper cites.
Isoperimetric problems for convex bodies and a localization lemma
Kannan, R., Lovász, L., and Simonovits, M · 1995
Earlier work this paper cites.
Statistical Inference Based on Divergence Measures
Pardo, L · 2005
Earlier work this paper cites.
Log-concave observers
Henningsson, T. and Åström, K · 2006
Earlier work this paper cites.
Denoising diffusion probabilistic models
Ho, J., Jain, A., and Abbeel, P · 2006
Earlier work this paper cites.
Log-concavity and strong log-concavity: A review
Saumard, A. and Wellner, J. A · 2014
Earlier work this paper cites.
Deep unsupervised learning using nonequilibrium thermodynamics
Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S · 2015
Earlier work this paper cites.
Membership inference attacks against machine learning models
Shokri, R., Stronati, M., Song, C., and Shmatikov, V · 2017
Earlier work this paper cites.
Beyond log-concavity: Provable guarantees for sampling multi-modal distributions using simulated tempering langevin monte carlo
Lee, H., Risteski, A., and Ge, R · 2018
Earlier work this paper cites.
Denoising diffusion probabilistic models
Ho, J., Jain, A., and Abbeel, P · 2020
Earlier work this paper cites.
Score-based generative modeling through stochastic differential equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., and Poole, B · 2020
Earlier work this paper cites.
Diffusion Schrödinger bridge with applications to score-based generative modeling
De Bortoli, V., Thornton, J., Heng, J., and Doucet, A · 2021
Earlier work this paper cites.
Diffusion models beat gans on image synthesis
Dhariwal, P. and Nichol, A · 2021
Earlier work this paper cites.
Learning transferable visual models from natural language supervision, 2021
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I · 2021
Earlier work this paper cites.
Generative modeling with denoising auto-encoders and Langevin sampling
Block, A., Mroueh, Y., and Rakhlin, A · 2022
Cited alongside, same era.
Chen, H., Lee, H., and Lu, J · 2022
Cited alongside, same era.
Perception prioritized training of diffusion models
Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., and Yoon, S · 2022
Cited alongside, same era.
Convergence of denoising diffusion models under the manifold hypothesis
De Bortoli, V · 2022
Cited alongside, same era.
Convergence for score-based generative modeling with polynomial complexity
Lee, H., Lu, J., and Tan, Y · 2022
Cited alongside, same era.
Let us build bridges: understanding and extending diffusion generative models
Sampling multimodal distributions with the vanilla score: Benefits of data-based initialization
Koehler, F. and Vuong, T.-D · 2023
Later among the works it cites.
Convergence of score-based generative modeling for general data distributions
Lee, H., Lu, J., and Tan, Y · 2023
Later among the works it cites.
Zero-shot machine-generated image detection using sinks of gradient flows
Li, M. and Wang, J · 2023
Later among the works it cites.
MoPe: Model perturbation based privacy attacks on language models
Li, M., Wang, J., Wang, J., and Neel, S · 2023
Later among the works it cites.
Stable bias: Analyzing societal representations in diffusion models, 2023
Luccioni, A. S., Akiki, C., Mitchell, M., and Jernite, Y · 2023
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Liu, X., Wu, L., Ye, M., and Liu, Q · 2022
Cited alongside, same era.
SDEdit: Guided image synthesis and editing with stochastic differential equations
Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., and Ermon, S · 2022
Cited alongside, same era.
Score-based generative models detect manifolds
Pidstrigach, J · 2022
Cited alongside, same era.
Convergence in KL divergence of the inexact Langevin algorithm with application to score-based generative models
Wibisono, A. and Yang, K. Y · 2022
Cited alongside, same era.
Extracting training data from diffusion models
Carlini, N., Hayes, J., Nasr, M., Jagielski, M., Sehwag, V., Tramèr, F., Balle, B., Ippolito, D., and Wallace, E · 2023
Cited alongside, same era.
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
Chen, S., Chewi, S., Li, J., Li, Y., Salim, A., and Zhang, A · 2023
Cited alongside, same era.
Analysis of learning a flow-based generative model from limited sample complexity
Cui, H., Krzakala, F., Vanden-Eijnden, E., and Zdeborová, L · 2023
Cited alongside, same era.
Mitchell, E., Lee, Y., Khazatsky, A., Manning, C. D., and Finn, C · 2023
Later among the works it cites.
How deep neural networks learn compositional data: The random hierarchy model
Petrini, L., Cagnetta, F., Tomasini, U. M., Favero, A., and Wyart, M · 2023
Later among the works it cites.
Spontaneous symmetry breaking in generative diffusion models
Raya, G. and Ambrogioni, L · 2023
Later among the works it cites.
High-dimensional statistics, 2023
Rigollet, P. and Hutter, J.-C · 2023
Later among the works it cites.
Learning mixtures of gaussians using the ddpm objective
Shah, K., Chen, S., and Klivans, A · 2023
Later among the works it cites.
Dynamical regimes of diffusion models, 2024
Biroli, G., Bonnaire, T., de Bortoli, V., and Mézard, M · 2024
Closest in time.
Interpreting clip’s image representation via text-based decomposition, 2024
Gandelsman, Y., Efros, A. A., and Steinhardt, J · 2024
Closest in time.
Towards a mathematical theory for consistency training in diffusion models
Li, G., Huang, Z., and Wei, Y · 2024
Closest in time.
A phase transition in diffusion models reveals the hierarchical nature of data, 2024
Sclocchi, A., Favero, A., and Wyart, M · 2024
Closest in time.