3 papers
cs.CL2026
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +274
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
cs.CV2026
Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
Roussel Desmond Nzoyem, Mauro Comi
Training world models on vast quantities of unlabelled videos is a critical step toward fully autonomous intelligence. However, the prevailing paradigm of encoding raw pixels into…
cs.RO2025
Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data
Ben Moran, Mauro Comi, Arunkumar Byravan +4
Creating accurate, physical simulations directly from real-world robot motion holds great value for safe, scalable, and affordable robot learning, yet remains exceptionally challen…