collaborators

7 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.LG2026

Efficient LLM Moderation with Multi-Layer Latent Prototypes

Maciej ChrabÄ szcz, Filip Szatkowski, Bartosz Wójcik +3

Although modern LLMs are aligned with human values during post-training, robust moderation remains essential to prevent harmful outputs at deployment time. Existing approaches suff…

cs.CV2026

Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval

Alicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert +2

While retrieval is a core function of vision-language models, continually updating these models for retrieval tasks remains critically underexplored. Existing work often approaches…

cs.LG2026

Rethinking Calibration for Early-Exit Neural Networks

Piotr Kubaty, Filip Szatkowski, Grzegorz Choczyński +2

Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enough. Most methods rely on confide…

cs.LG2026

Universal Properties of Activation Sparsity in Modern Large Language Models

Filip Szatkowski, Patryk Będkowski, Alessio Devoto +5

Activation sparsity is an intriguing property of deep neural networks that has been extensively studied in ReLU-based models, due to its advantages for efficiency, robustness, and…

cs.CV2025

ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts

Patryk Będkowski, Jan Dubiński, Filip Szatkowski +3

Simulating detector responses is a crucial part of understanding the inner workings of particle collisions in the Large Hadron Collider at CERN. Such simulations are currently perf…