Paper Information | SBC BOOKS

Fill in your paper information

Language (*)

Title (*)

Keywords (*)

Abstract (*)

Modelos generativos têm recebido atenção significativa na comunidade de inteligência artificial e estão expandindo seu alcance para além da esfera técnica. Entre as abordagens mais recentes e promissoras, destacam-se os Modelos de Difusão, que adotam uma estratégia inovadora de modelagem generativa: adicionam progressivamente ruído de intensidades variadas aos dados — uma técnica inspirada em dinâmicas estocásticas e conhecida como difusão — e aprendem a reverter essas perturbações. A partir de uma amostra de ruído puro, esses modelos podem gerar novas imagens, textos, vídeos e diversos outros tipos de dados com qualidade notavelmente alta, superando métodos anteriores do estado da arte em muitas dessas tarefas. Este minicurso oferece uma introdução formal e acessível aos fundamentos dos modelos de difusão, abordando os princípios probabilísticos que os sustentam — como a divergência de Kullback-Leibler, a dinâmica de Langevin e o score matching — além de intuições visuais que auxiliam na compreensão. Em seguida, apresenta uma visão geral do estado da arte na área, incluindo técnicas de condicionamento e modelos de difusão latentes. Por fim, o curso discute as oportunidades de pesquisa e aplicações que essa área em rápida evolução tem a oferecer.

Pages (*)

File Link

English Information

Title

Keywords

Abstract

Generative models have received significant attention in the artificial intelligence community and are expanding their reach beyond the technical sphere. Among the most recent and promising approaches are Diffusion Models, which adopt an innovative generative modeling strategy: they progressively add noise of varying intensities to the data—a technique inspired by stochastic dynamics and known as diffusion—and then learn to reverse these perturbations. Starting from a pure noise sample, these models can generate new images, text, videos, and various other types of data with remarkably high quality, outperforming previous state-of-the-art methods in many of these tasks. This minicourse provides a formal and accessible introduction to the foundations of diffusion models, covering their underlying probabilistic principles — such as Kullback-Leibler divergence, Langevin dynamics, and score matching — as well as visual intuitions to aid comprehension. Then, it presents an overview of the current state of the art in the field, including conditioning techniques and latent diffusion models. Finally, the course discusses the research opportunities and applications that this rapidly evolving area has to offer.

(*) To change the order drag the item to the new position.

Authors

#	Name
1	Samir Chaves(samirchaves@insightlab.ufc.br)
2	Jose Macêdo(jose.macedo@insightlab.ufc.br)
3	Regis Magalhães( regis@insightlab.ufc.br )
4	Vaux Gomes(vauxsandino@gmail.com)
5	César Lincoln C. Mattos(cesarlincoln@dc.ufc.br)

(*) To change the order drag the item to the new position.

Reference

#	Reference
1	Aali, A., Arvinte, M., Kumar, S., and Tamir, J. I. (2023). Solving inverse problems with score-based generative priors learned from noisy data. In 2023 57th Asilomar Conference on Signals, Systems, and Computers, pages 837-843.
2	Bishop, C. M. and Bishop, H. (2024). Deep Learning - Foundations and Concepts. Springer.
3	Chung, H., Kim, J., Mccann, M. T., Klasky, M. L., and Ye, J. C. (2023). Diffusion posterior sampling for general noisy inverse problems. In The Eleventh International Conference on Learning Representations.
4	Chung, H., Kim, J., Park, G. Y., Nam, H., and Ye, J. C. (2025). CFG++: Manifold-constrained classifier free guidance for diffusion models. In The Thirteenth International Conference on Learning Representations.
5	Chung, H., Sim, B., Ryu, D., and Ye, J. C. (2022). Improving diffusion models for inverse problems using manifold constraints. In Oh, A. H., Agarwal, A., Belgrave, D., and Cho, K., editors, Advances in Neural Information Processing Systems
6	Corso, G., St¨ark, H., Jing, B., Barzilay, R., and Jaakkola, T. S. (2023). Diffdock: Diffusion steps, twists, and turns for molecular docking. In The Eleventh International Conference on Learning Representations.
7	Cox, D. and Hinkley, D. (1974). Theoretical Statistics. Chapman and Hall/CRC, New York, 1st edition.
8	Dhariwal, P. and Nichol, A. (2021a). Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780–8794.
9	Dhariwal, P. and Nichol, A. Q. (2021b). Diffusion models beat GANs on image synthesis. In Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J. W., editors, Advances in Neural Information Processing Systems.
10	Dinh, L., Krueger, D., and Bengio, Y. (2015). NICE: non-linear independent components estimation. In Bengio, Y. and LeCun, Y., editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Workshop Track Proceedings.
11	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations.
12	Fefferman, C., Mitter, S., and Narayanan, H. (2013). Testing the manifold hypothesis.
13	Gong, S., Li, M., Feng, J., Wu, Z., and Kong, L. (2022). Diffuseq: Sequence to sequence text generation with diffusion models. arXiv preprint arXiv:2210.08933.
14	Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2, NIPS’14, page 2672–2680, Cambridge, MA, USA. MIT Press.
15	Ho, J., Jain, A., and Abbeel, P. (2020). Denoising diffusion probabilistic models. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA. Curran Associates Inc.
16	Ho, J. and Salimans, T. (2021). Classifier-free diffusion guidance. In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications.
17	Ho, J., Salimans, T., Gritsenko, A. A., Chan, W., Norouzi, M., and Fleet, D. J. (2022). Video diffusion models. In Oh, A. H., Agarwal, A., Belgrave, D., and Cho, K., editors, Advances in Neural Information Processing Systems.
18	Hyvärinen, A. (2005). Estimation of non-normalized statistical models by score matching. J. Mach. Learn. Res., 6:695–709.
19	Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., and Saul, L. K. (1998). An Introduction to Variational Methods for Graphical Models, pages 105–161. Springer Netherlands, Dordrecht.
20	Kingma, D. P. and Gao, R. (2023). Understanding diffusion objectives as the ELBO with simple data augmentation. In Thirty-seventh Conference on Neural Information Processing Systems.
21	Kingma, D. P., Salimans, T., Poole, B., and Ho, J. (2021). On density estimation with diffusion models. In Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J. W., editors, Advances in Neural Information Processing Systems.
22	Kingma, D. P. and Welling, M. (2022). Auto-encoding variational bayes.
23	Kotelnikov, A., Baranchuk, D., Rubachev, I., and Babenko, A. (2023). TabDDPM: Modelling tabular data with diffusion models.
24	Li, X. L., Thickstun, J., Gulrajani, I., Liang, P., and Hashimoto, T. (2022). Diffusion-LM improves controllable text generation. In Oh, A. H., Agarwal, A., Belgrave, D., and Cho, K., editors, Advances in Neural Information Processing Systems.
25	Li, Z., Huang, Q., Yang, L., Shi, J., Yang, Z., van Stein, N., Bäck, T., and van Leeuwen, M. (2025). Diffusion models for tabular data: Challenges, current progress, and future directions.
26	Liu, T., Fan, J., Tang, N., Li, G., and Du, X. (2024). Controllable tabular data synthesis using diffusion models. Proc. ACM Manag. Data, 2(1).
27	Liu, X., Gong, C., and qiang liu (2023). Flow straight and fast: Learning to generate and transfer data with rectified flow. In The Eleventh International Conference on Learning Representations.
28	Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., and Zhu, J. (2022). DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps. In Oh, A. H., Agarwal, A., Belgrave, D., and Cho, K., editors, Advances in Neural Information Processing Systems.
29	Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., and Zhu, J. (2023). DPM-solver++: Fast solver for guided sampling of diffusion probabilistic models.
30	Luo, Z., Chen, D., Zhang, Y., Huang, Y., Wang, L., Shen, Y., Zhao, D., Zhou, J., and Tan, T. (2023). Videofusion: Decomposed diffusion models for high-quality video generation. arXiv preprint arXiv:2303.08320.
31	Murphy, K. P. (2022). Probabilistic Machine Learning: An introduction. MIT Press.
32	Nichol, A. Q. and Dhariwal, P. (2021). Improved denoising diffusion probabilistic models.
33	Patel, L., Kraft, P., Guestrin, C., and Zaharia, M. (2024). Acorn: Performant and predicate-agnostic search over vector embeddings and structured data. Proc. ACM Manag. Data, 2(3).
34	Peebles, W. and Xie, S. (2023). Scalable diffusion models with transformers. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 4172–4182.
35	Prince, S. J. (2023). Understanding Deep Learning. The MIT Press.
36	Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical text-conditional image generation with clip latents.
37	Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2021). High-resolution image synthesis with latent diffusion models.
38	Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham. Springer International Publishing.
39	Saharia, C., Chan, W., Saxena, S., Lit, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Gontijo-Lopes, R., Salimans, T., Ho, J., Fleet, D. J., and Norouzi, M. (2022). Photorealistic text-to-image diffusion models with deep language understanding. In Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS ’22, Red Hook, NY, USA. Curran Associates Inc.
40	Sattarov, T., Schreyer, M., and Borth, D. (2023). Findiff: Diffusion models for financial tabular data generation. In Proceedings of the Fourth ACM International Conference on AI in Finance, ICAIF ’23, page 64–72, New York, NY, USA. Association for Computing Machinery.
41	Shi, R., Wang, Y., Du, M., Shen, X., Chang, Y., and Wang, X. (2025). A comprehensive survey of synthetic tabular data generation.
42	Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium hermodynamics. In International conference on machine learning, pages 2256–2265. pmlr.
43	Song, J., Meng, C., and Ermon, S. (2021a). Denoising diffusion implicit models. In International Conference on Learning Representations.
44	Song, Y. and Ermon, S. (2019). Generative modeling by estimating gradients of the data distribution. Curran Associates Inc., Red Hook, NY, USA.
45	Song, Y., Garg, S., Shi, J., and Ermon, S. (2019). Sliced score matching: A scalable approach to density and score estimation. CoRR, abs/1905.07088.
46	Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., and Poole, B. (2021b). Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations.
47	Tang, Z., Bao, J., Chen, D., and Guo, B. (2025). Diffusion models without classifier-free guidance.
48	Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 6000–6010, Red Hook, NY, USA. Curran Associates Inc.
49	Vignac, C., Krawczuk, I., Siraudin, A., Wang, B., Cevher, V., and Frossard, P. (2023). Digress: Discrete denoising diffusion for graph generation. In The Eleventh International Conference on Learning Representations.
50	Villaizán-Vallelado, M., Salvatori, M., Segura, C., and Arapakis, I. (2025). Diffusion models for tabular data imputation and synthetic data generation. ACM Trans. Knowl. Discov. Data, 19(6).
51	Vincent, P. (2011). A connection between score matching and denoising autoencoders. Neural Comput., 23(7):1661–1674.
52	Wainwright, M. J. and Jordan, M. I. (2008). Graphical models, exponential families, and variational inference. Found. Trends Mach. Learn., 1(1–2):1–305.
53	Watson, J. L., Juergens, D., Bennett, N. R., Trippe, B. L., Yim, J., Eisenach, H. E., Ahern, W., Borst, A. J., Ragotte, R. J., Milles, L. F., Wicky, B. I. M., Hanikel, N., Pellock, S. J., Courbet, A., Sheffler, W., Wang, J., Venkatesh, P., Sappington, I., Torres, S. V., Lauko, A., De Bortoli, V., Mathieu, E., Ovchinnikov, S., Barzilay, R., Jaakkola, T. S., DiMaio, F., Baek, M., and Baker, D. (2023). De novo design of protein structure and function with RFdiffusion. Nature, 620(7976):1089–1100.
54	Wu, X., Pang, Y., Liu, T., and Wu, S. (2025). Winning the midst challenge: New membership inference attacks on diffusion models for tabular data synthesis.
55	Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., and Yang, M.-H. (2024). Diffusion models: A comprehensive survey of methods and applications.

Paper Registration

Fill in your paper information

English Information

Authors

Reference