nimdoc's profile picture. #AI engineering, working on applied #ComputerVision. #RecSys researcher. PhD fr @KTHuniversity. opinions expressed (if any!) are my own.

Nima Dokoohaki

@nimdoc

#AI engineering, working on applied #ComputerVision. #RecSys researcher. PhD fr @KTHuniversity. opinions expressed (if any!) are my own.

Nima Dokoohaki reposted

The hot topic at #ICCV2025 was World Models. They come in different flavors — (interactive) video models, neural simulators, reconstruction models, etc. — but the overarching goal is clear: Generative AI that predict and simulate how the real world works.


Nima Dokoohaki reposted

Evolution of Deep Learning by Hand ✍️ As my tribute to Geoff Hinton's Nobel Prize, I drew this animation to illustrate the key idea behind Hinton's major contributions to deep learning over the years, with artistic liberty. ---- 100% original, made by hand ✍️ Join 40k readers…


Nima Dokoohaki reposted

< Choosing a Vision Backbone > your model’s backbone is its perspective pick ResNet, and it sees in edges pick a ViT, and it sees in patches the backbone decides how your model thinks here are some of the most practical backbones and when you should choose them, from the…

chesterzelaya's tweet image. &amp;lt; Choosing a Vision Backbone &amp;gt;

your model’s backbone is its perspective

pick ResNet, and it sees in edges
pick a ViT, and it sees in patches

the backbone decides how your model thinks

here are some of the most practical backbones and when you should choose them, from the…
chesterzelaya's tweet image. &amp;lt; Choosing a Vision Backbone &amp;gt;

your model’s backbone is its perspective

pick ResNet, and it sees in edges
pick a ViT, and it sees in patches

the backbone decides how your model thinks

here are some of the most practical backbones and when you should choose them, from the…

Nima Dokoohaki reposted

In 2016 Geoffrey Hinton said “we should stop training radiologists now" since AI would soon be better at their jobs. He was right: models have outperformed radiologists on benchmarks for ~a decade. Yet radiology jobs are at record highs, with an average salary of $520k. Why?

deenamousa's tweet image. In 2016 Geoffrey Hinton said “we should stop training radiologists now&quot; since AI would soon be better at their jobs.

He was right: models have outperformed radiologists on benchmarks for ~a decade.

Yet radiology jobs are at record highs, with an average salary of $520k.

Why?

Nima Dokoohaki reposted

Code World Model: producing code by imagining the effect of executing instructions and planning instructions that produce the desired effect.

(🧵) Today, we release Meta Code World Model (CWM), a 32-billion-parameter dense LLM that enables novel research on improving code generation through agentic reasoning and planning with world models. ai.meta.com/research/publi…



Nima Dokoohaki reposted

Can AI help understand how the brain learns to see the world? Our latest study, led by @JRaugel from FAIR at @AIatMeta and @ENS_ULM, is now out! 📄 arxiv.org/pdf/2508.18226 🧵 A thread:


Nima Dokoohaki reposted

Energy-Based Transformers are Scalable Learners and Thinkers

_akhaliq's tweet image. Energy-Based Transformers are Scalable Learners and Thinkers

Nima Dokoohaki reposted

beautiful explanations of self-attention 💡 wild that one little math hack made all these possible.

rohanpaul_ai's tweet image. beautiful explanations of self-attention 💡

wild that one little math hack made all these possible.

Today is the day I truly understood why attention works Not just for words, but images, audio, video. But everything else.

goyal__pramod's tweet image. Today is the day I truly understood why attention works

Not just for words, but images, audio, video. But everything else.


Nima Dokoohaki reposted

The official trailer for the official Python documentary is out!!! ❤️to Ida.

The trailer for "Python, the Documentary" by @CultRepo premieres today! 🔥🐍 From its origins in the Netherlands to powering AI at top global companies, this is Python's story. 🎥 The film premieres at @EuroPython in July! Subscribe to @CultRepo's YouTube channel for updates!…



Nima Dokoohaki reposted

“AI Engineering is just software engineering with AI models thrown into the stack” - @abacaj in the book AI Engineering by @chipro Totally agree - and it’s why learning how to integrate LLMs is such a big win for devs!

GergelyOrosz's tweet image. “AI Engineering is just software engineering with AI models thrown into the stack”

- @abacaj in the book AI Engineering by @chipro

Totally agree - and it’s why learning how to integrate LLMs is such a big win for devs!

Nima Dokoohaki reposted

Training of a 2 → 100 → 2 → 5 fully connected ReLU neural net via cross-entropy minimisation. • it starts outputting small embeddings • around epoch 300 learns an identity function • takes 1700 epochs more to unwind the data manifold


Nima Dokoohaki reposted

We trained a graph-native AI, then let it reason for days, forming a dynamic relational world model on its own - no pre-programming. Emergent hubs, small-world properties, modularity, & scale-free structures arose naturally. The model then exploited compositional reasoning &…


Nima Dokoohaki reposted

Fourier transform. Visualized. This is the secret to how human memory is encoded.


Nima Dokoohaki reposted

Yann LeCun on architectures that could lead to AGI

rohanpaul_ai's tweet image. Yann LeCun on architectures that could lead to AGI

Nima Dokoohaki reposted

Deep Research just dropped a wild list... 20 jobs that OpenAI o3 will replace humans.

minchoi's tweet image. Deep Research just dropped a wild list...

20 jobs that OpenAI o3 will replace humans.

Nima Dokoohaki reposted

LLM running on Windows 98 PC 26 year old hardware with Intel Pentium II CPU and 128MB RAM. Uses llama98.c, our custom pure C inference engine based on @karpathy llama2.c Code and DIY guide 👇


Watch this tedtalk if you follow current trends in AI. I had the very pleasure of following @jengolbeck work during my research on online trust and I agree with her every word. youtu.be/Tq6_7XyCyyI?si…

nimdoc's tweet card. Is AI Progress Stuck? | Jennifer Golbeck | TED

youtube.com

YouTube

Is AI Progress Stuck? | Jennifer Golbeck | TED


Nima Dokoohaki reposted

Python is now #1 like it should be.

svpino's tweet image. Python is now #1 like it should be.

Nima Dokoohaki reposted

Brain studies show that language is not essential for the cognitive processes that underlie thought via @sciam scientificamerican.com/article/you-do…


Nima Dokoohaki reposted

This year’s #NobelPrize laureate in physics John Hopfield created an associative memory that can store and reconstruct images and other types of patterns in data. The Hopfield network can store patterns and has a method for recreating them. When the network is given an…

NobelPrize's tweet image. This year’s #NobelPrize laureate in physics John Hopfield created an associative memory that can store and reconstruct images and other types of patterns in data.

The Hopfield network can store patterns and has a method for recreating them. When the network is given an…

Loading...

Something went wrong.


Something went wrong.