./whoami
Hi! I’m Giorgio. I am a second year PhD student at Sapienza, in Rome, at the Gladia lab under supervision of prof. Emanuele Rodolà.
After dark, I am a passionate music maker and listener, lover of photogaraphy and experimental art.
I love logic a bit too much, reverse engineering, solving problems and putting my skills to the test whenever I can.
~/research
At the moment, my research is focused on:
- Audio generative models, with special focus on controllability, conditioning sources and strategies, and representation learning for audio;
- Optimization and training dynamics of large models in continual learning;
- Quantization of transformer models.
~/publications
STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
G. Strano, C. Ballanti, D. Crisostomi, M. Mancusi, L. Cosmo, E. Rodolà.
LoopGen: Training-Free Loopable Music Generation
D. Marincione, G. Strano, D. Crisostomi, R. Ribuoli, E. Rodolà.
Membership and Dataset Inference Attacks on Large Audio Generative Models
Jakub Proboszcz, Paweł Kochanski, Karol Korszun, Donato Crisostomi, Giorgio Strano, Emanuele Rodolà, Kamil Deja, Jan Dubinski.
The dynamics of forgetting
G. Strano, F. Pappone, D. Crisostomi, E. Rodolà.
Activation Patching for Interpretable Steering in Music Generation
S. Facchiano, G. Strano, D. Crisostomi, I. Tallini, T. Mencattini, F. Galasso, E. Rodolà.
~/fun
Tripod is a small and portable, fully-convolutional 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.