./whoami
My name is Giorgio Strano.
I was born and currently live in Rome, Italy, where I study Computer Science at Sapienza University.
My journey is in pursuit of a deeper understanding of human and artificial intelligence to explore challenges that once seemed unsolvable, redefining the realms of what is possible with modern technology.
I love logic a bit too much, reverse engineering, solving problems and putting my skills to the test whenever I can.
~/uni
After completing with honors my Bachelor’s in Computer Science at Sapienza in 2021, I continued with a Master’s degree especially focused on theoretical computer science and artificial intelligence, with a particular interest in deep learning.
As of June 2023, I am taking my last few exams, and I intend to spend the next academic year working on my Master’s thesis.
Some of the topics that I have recently studied and I found extremely fascinating include:
- Multimodal deep learning, with particular interest on latent space analysis and interpretation, fully convolutional architectures, VQ-VAEs, diffusion models and transformers
- Advanced algorithms
- Graph theory
- Intensive computation and quantum computing
- Natural language processing
- Computer graphics, especially physically based volumetric path-tracing
Here follows a list of some of my favorite projects from the last couple of years, with a brief description. Code, results, and other projects are on my GitHub.
~/dev
Still a work in progress, Tripod will be a small and portable deep learning model to sharpen and correct the focus of real-world photographs.
A physically based volumetric path tracer written in Julia from scratch with my friend and colleague Antonio Gargiulo. It is inspired from Yocto/GL, the rendering engine developed by our professor, Fabio Pellacini. It renders complex 3D scenes accurately, with almost negligible slowdown compared to a fairly optimized equivalently capable C++ implementation.
This is a re-implementation, with more experiments, and extended to different videogame environments of the paper World Models.
During my NLP course, held by Roberto Navigli, I tackled the challenge of GAP-coreference, achieving results very close to state-of-the-art with a distilled transformer that could fit in 8GB of VRAM.
A transformer-free approach to named entity resolution, using bidirectional LSTMs on different type of non-contextualized embeddings (W2V, Glove), improved with character embedding and a Conditional Random Field (CRF).
An implementation from scratch (…meaning from vanilla pytorch) of the Double Deep Q Learning algorithm, applied to the classic first ever Super Mario Bros videogame for the NES.
For my Bachelor’s thesis I devloped this project with the Vision Lab of Sapienza: Adaptive Neural Networks Via Reinforcement Learning. It explores the idea of networks able to automatically resize during training to maximize the efficiency of crucial neurons and reduce the overhead of inactive ones, achieving automatic in-itinere pruning and extension of networks based on the complexity of the task.