Nima Dokoohaki
@nimdoc
#AI engineering, working on applied #ComputerVision. #RecSys researcher. PhD fr @KTHuniversity. opinions expressed (if any!) are my own.
You might like
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.
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…
< 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…
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?
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…
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:
Energy-Based Transformers are Scalable Learners and Thinkers
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.
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!…
“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!
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
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 &…
Fourier transform. Visualized. This is the secret to how human memory is encoded.
Yann LeCun on architectures that could lead to AGI
Deep Research just dropped a wild list... 20 jobs that OpenAI o3 will replace humans.
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…
youtube.com
YouTube
Is AI Progress Stuck? | Jennifer Golbeck | TED
Brain studies show that language is not essential for the cognitive processes that underlie thought via @sciam scientificamerican.com/article/you-do…
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…
United States Trends
- 1. Cam Coleman 2,579 posts
- 2. Iowa 27.6K posts
- 3. Dante Moore 3,067 posts
- 4. Indiana 41.8K posts
- 5. Penn State 25.5K posts
- 6. #UFCVegas111 8,554 posts
- 7. Mendoza 23.1K posts
- 8. Heisman 11K posts
- 9. Gus Johnson 7,827 posts
- 10. Mizzou 5,085 posts
- 11. Atticus Sappington N/A
- 12. #kufball N/A
- 13. #GoDucks 2,904 posts
- 14. UConn 4,497 posts
- 15. Sayin 71.6K posts
- 16. Lance 31.1K posts
- 17. Sounders 1,066 posts
- 18. Texas A&M 6,342 posts
- 19. Aggies 2,790 posts
- 20. Fran Brown N/A
Something went wrong.
Something went wrong.