LLaVA
It means Large Language and Vision Assistant, basically we are talking about an LMM (Large Multimodal Model) which connects a vision encoder with an LLM for ...
Blog
2025
GPT-OSS
This will be a simple, fast and somewhat funny blog post. Take it as it is, and thanks for reading it 
JAX
Hey, this won’t be a tutorial on JAX, how to use it, or anything like that. It’s more about understanding the importance of the paradigm shift, and why it ex...
DINOv3
The underlying idea behind the advancements of DINOv3 is simple, and this is beautiful. Occam’s Razor is always present and guides daily decisions. So, today...
NVIDIA NV1 (and NV2)
These days, the NVIDIA DGX Spark has been given to selected people for let them try it. It allows to perform AI inference locally; well the DGX is awesome (r...
Hardware and Software of Lumino
This will be an important discussion: we are going to decide how to build Lumino! 
Building My Own Robotic Pet
Just graduated 
with my master’s degree and nothing planned in the short term. How to make the best use of this free time? Well, what could be ...
Decoding Images: Pills Fourier Transform for 2D & 3D Image Analysis
Today we’ll explore how a classic mathematical tool reveals rich information about patterns, textures, and structures, especially when dealing with noisy or ...
2024
A really awsome blog
Hello world, this is my first Jekyll blog post.