iiinova — where your digital self keeps evolving

Reposted by Soran Ghaderi

Grant Sanderson @3blue1brown.com · 25/07/2025

New video on the details of diffusion models: youtu.be/iv-5mZ_9CPY Produced by Welch Labs, this is the first in a short series of 3b1b this summer. I enjoyed providing editorial feedback throughout the last several months, and couldn't be happier with the result.

youtu.be

But how do AI videos actually work? | Guest video by @WelchLabsVideo

YouTube video by 3Blue1Brown

214413

Reposted by Soran Ghaderi

AI Conference DL Countdown @dlcountdown.bsky.social · 27/06/2025

AAAI'26 (abs): 29 days. WACV'26 (R1,reg): 15 days. WACV'26 (R1,paper): 22 days. AAAI'26 (paper): 36 days. 3DV'26: 52 days. WACV'26 (R2,reg): 78 days. WACV'26 (R2,paper): 85 days. ICLR'26 (abs): 85 days. ICLR'26 (paper): 90 days.

021

Reposted by Soran Ghaderi

François Fleuret @francois.fleuret.org · 28/04/2025

I asked "on the other platform" what were the most important improvements to the original 2017 transformer. That was quite popular and here is a synthesis of the responses:

420743

Soran Ghaderi @soranghaderi.bsky.social · 21/04/2025

📌 The process of learning the energy landscape (potential field) of an EBM. Trained using TorchEBM v0.3.0! I will be uploading more experimental animations for different configs and datasets—Gaussian Mixture with 4 components.

110

Reposted by Soran Ghaderi

NeurIPS Conference @neuripsconf.bsky.social · 13/04/2025

The NeurIPS Call for Workshops is now live. Proposals are due May 30 AoE, with acceptance notification on July 4 AoE. neurips.cc/Conferences/...  If you plan to submit a proposal for a workshop, please read our detailed guidance in our new blog post: blog.neurips.cc/2025/04/12/g...

neurips.cc

Call For Workshops 2025

Sat Dec 6 and Sun Dec 7, 2025

02316

Soran Ghaderi @soranghaderi.bsky.social · 13/04/2025

📌 Training an EBM on a Gaussian Mixture Read this blog post on how to train an energy-based model (EBM) on a 2D Gaussian mixture distribution using the TorchEBM library. 👇 #EBM #OpenSource #DeepLearning #GenerativeAI

120

Soran Ghaderi @soranghaderi.bsky.social · 13/04/2025

Watch this mini energy-based model learning a Gaussian mixture distribution! ✨ 📌 This is the first model trained using #TorchEBM - The probability density (blue colors) learned by the EBM sharpens around the white circles. - Red dots get closer to the GM dist. Link 👇 #EBM #GenerativeAI

110

Soran Ghaderi @soranghaderi.bsky.social · 06/04/2025

The new version of the 🟢 #TorechEBM docs is now out. There are some tutorials on #EBMs there. I'm thinking about adding support for #diffusion- and #flow-based methods. 📌Collaboration's welcome! Link: ...

100

Soran Ghaderi @soranghaderi.bsky.social · 29/03/2025

My new post on Hamiltonian mechanics and HMC. Breaks down the math to with bits of visualization.

020

Soran Ghaderi @soranghaderi.bsky.social · 15/03/2025

📌 Different quadratic forms in two variables show how different covariance matrices influence the shape of these forms. I'll publish an intro to Hamiltonian mechanics and Monte Carlo on the #TorchEBM lib blog soon. #Hamiltonian #Sampling #EnergyBasedModels #MCMC #GenerativeAI

120

Soran Ghaderi @soranghaderi.bsky.social · 15/03/2025

Symmetries write particles into existence.

110

Soran Ghaderi @soranghaderi.bsky.social · 14/03/2025

The phase space is a mathematical space where we can represent a physical system's set of possible states.

010

Reposted by Soran Ghaderi

Miles Cranmer @milescranmer.bsky.social · 15/01/2025

I think the “hammer in search of a nail” style of science is perpetually underrated. From Leeuwenhoek’s lens to DeepMind’s AlphaFold, powerful tools chasing problems spark revolutions. If your hammer is Mjölnir, why not swing for the grandest problem?

1225

Reposted by Soran Ghaderi

Mathurin Massias @mathurinmassias.bsky.social · 27/11/2024

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

1235299

Reposted by Soran Ghaderi

sbi - Simulation-based inference @sbi-devs.bsky.social · 18/11/2024

Hello, world! We are a community-developed toolkit that performs Bayesian inference for simulators. We support a broad range of methods (NPE, NLE, NRE, amortized and sequential), neural network architectures (flows, diffusion models), samplers, and diagnostics. Join us!

1268

Reposted by Soran Ghaderi

Hannes Stark @hannes-stark.bsky.social · 24/11/2024

Tomorrow (Monday) Akhil Premkumar will present his "Neural Entropy" arxiv.org/abs/2409.03817 Join us on zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg

0185

Reposted by Soran Ghaderi

AI Conference DL Countdown @dlcountdown.bsky.social · 24/11/2024

SIGGRAPH'25 (form): 53 days. RSS'25 (abs): 54 days. SIGGRAPH'25 (paper-md5): 60 days. RSS'25 (paper): 61 days. ICML'25: 67 days. ICCV'25: 102 days.

095