Gianluigi Silvestri

[Chieh-Hsin (Jesse) Lai @JCJesseLai]

Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on!

📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon.

It traces the core ideas that shaped diffusion modeling and explains how today’s models work, why they work, and where they’re heading.

🧵You’ll find the link and a few highlights in the thread.
We’d love to hear your thoughts and join some discussions!

⚡ Stay tuned for our markdown version, where you can drop your comments!

[anandmaj @Almondgodd]

I spent the past month reimplementing DeepMind’s Genie 3 world model from scratch

Ended up making TinyWorlds, a 3M parameter world model capable of generating playable game environments

demo below + everything I learned in thread (full repo at the end)👇🏼

[Luca Ambrogioni @LucaAmb]

1/2) Have you have noticed that the forward process in a diffusion model looks a lot like the reparameterization trick in VAEs?
It turns out that there is a deep connection!

Curious? Watch our new vedio in the Generative Memory Lab channels

(link below)

[Gianluigi Silvestri @gisilvs]

@CSProfKGD @ArashVahdat What talk was this? I missed it :(

[Gianluigi Silvestri @gisilvs]

New preprint out! Reach out if you are interested, or let's grab a coffee at ICML this week!

[Luca Ambrogioni @LucaAmb]

1/3) I am biased, but I think this is going to be big!

CoVAE: Consistency Training of Variational Autoencoders

We unify consistency models with VAEs to obtain a powerful and elegant generative autoencoder!

The brainchild of the brilliant @gisilvs (who is looking for jobs!)

[Gianluigi Silvestri @gisilvs]

@rgilman33 How are the VAEs fixed in SD3.5 and FLUX? Are there papers/open source codes where I can find the fix?

[Gianluigi Silvestri @gisilvs]

@canaesseth @LucaAmb @SonyAI_global @JCJesseLai @takiko_san @mittu1204 Thanks for sharing! Your work is very interesting and quite related to ours, we will add the reference in the next updated version of the paper.

[Luca Ambrogioni @LucaAmb]

I am very happy to share our recent work on consistency model led my my brilliant PhD student @gisilvs during his internship at @SonyAI_global in collaboration with @JCJesseLai, @takiko_san and @mittu1204.

"Training Consistency Models with Variational Noise Coupling"

[Luca Ambrogioni @LucaAmb]

I am very happy to share:

" Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion"

We study the evolving latent geometry of diffusion by analyzing gaps in the Jacobian spectrum with statistical physics methods

Paper: https://t.co/yHerz5y4aO

[Luca Ambrogioni @LucaAmb]

Amazing presentation by Marvin Li on critical windows in diffusion models.

A work very closely related to our research on spontaneous symmetry breaking.

https://t.co/T66S9anPkq

[Luca Ambrogioni @LucaAmb]

Job alert! I am looking for a talented PhD student to do research on generative diffusion and its connections to statistical physics and memory.

Feel free to send me a PM if you need more info!

You can apply here:
https://t.co/SjNJLG3YOq

Otherwise, please retweet!

[Luca Ambrogioni @LucaAmb]

An amazing talk by @aaron_lou on diffusion language transformers.

Bracing for the era of large language diffusion!

https://t.co/NlmFLrLPGP

[Luca Ambrogioni @LucaAmb]

You should follow our Generative Memory Lab channel!

Plenty of content on generative models, diffusion models, associative memory!

https://t.co/8bfLuV05dB

[Luca Ambrogioni @LucaAmb]

A very insightful presentation about probabilistic Hopfield nets and their link with diffusion models!

https://t.co/QgbQTEB2II

[Gianluigi Silvestri @gisilvs]

@0razio @JustHuebotter go!

[Gianluigi Silvestri @gisilvs]

Another fantastic presentation, this time from @k_neklyudov!! You can watch it here: https://t.co/dj2p07hLFs

Thanks @k_neklyudov for the great talk and for answering all our questions 👏🙏!

[Luca Ambrogioni @LucaAmb]

Modern Hopfield networks are related to transformers, but did you know that they are mathematically equivalent to generative diffusion models?

Happy to share:
"In search of dispersed memories: Generative diffusion models are associative memory networks"

https://t.co/pHd3RjtG56

[Gianluigi Silvestri @gisilvs]

@shawshank_v @NeurIPSConf @1avr1e congrats! 👏👏

[Gianluigi Silvestri @gisilvs]

Fantastic presentation from @dblueeye on diffusion models with discrete diffusion process 👏👏 very clear explanation and promising results for their 'Blackout Diffusion'. Take a look at the presentation here https://t.co/4dTC04fOAM

[Gianluigi Silvestri @gisilvs]

Kicking off the new series of presentations with a super interesting talk by @aaron_lou on Reflected Diffusion Models! You can watch the recording here: https://t.co/nuYGVLr4Tc

Thank you so much @aaron_lou 🙏🙏