./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.
I am currently working on AI safety and decoding geometry and semantics in latent neural representations.
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:
- Geometry and semantics of latent neural representations;
- Optimization and training dynamics of large models in continual learning;
- Audio generative models, with special focus on controllability, conditioning sources and strategies, and representation learning for audio.
~/publications
Under blind review.
https://arxiv.org/abs/2606.00635
How Neural Losses Shape VAE Latents
G. Strano, L. Cerovaz, M. Mancusi, T. Mencattini, E. Rodolà.
ICML 2026.
https://arxiv.org/abs/2605.03929
PHALAR: Phasors for Learned Musical Audio Representations
D. Marincione, M. Mancusi, G. Strano, L. Cerovaz, D. Crisostomi, R. Ribuoli, E. Rodolà.
ISMIR 2025.
https://arxiv.org/abs/2504.05690
STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning
G. Strano, C. Ballanti, D. Crisostomi, M. Mancusi, L. Cosmo, E. Rodolà.
ISMIR 2025.
https://arxiv.org/abs/2504.04466
LoopGen: Training-Free Loopable Music Generation
D. Marincione, G. Strano, D. Crisostomi, R. Ribuoli, E. Rodolà.
GenProCC, AI4Music @ NeurIPS 2025.
https://arxiv.org/abs/2512.09654
Membership and Dataset Inference Attacks on Large Audio Generative Models
J. Proboszcz, P. Kochanski, K. Korszun, D. Crisostomi, G. Strano, E. Rodolà, K. Deja, J. Dubinski.
ArXiv 2025
https://arxiv.org/abs/2504.04479
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.
World Models
https://github.com/giorgioskij/world-models
This is a re-implementation, with more experiments, and extended to different videogame environments of the paper World Models.
NLP - Coreference resolution
https://github.com/giorgioskij/NLP-coreference-resolution
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.
NLP - Named Entity Recognition
https://github.com/giorgioskij/NLP-Named-Entity-Recognition
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).
Super Mario DDQN
https://github.com/giorgioskij/SuperMario-RL
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.