4 papers
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…
Private PoEtry: Private In-Context Learning via Product of Experts
Rob Romijnders, Mohammad Mahdi Derakhshani, Jonathan Petit +3
In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks with only a small set of examples at inference time, thereby avoiding task-specific fine-tuning…
A Probabilistic Approach to Pose Synchronization for Multi-Reference Alignment with Applications to MIMO Wireless Communication Systems
Rob Romijnders, Gabriele Cesa, Christos Louizos +2
From molecular imaging to wireless communications, the ability to align and reconstruct signals from multiple misaligned observations is crucial for system performance. We study th…
NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation
Rob Romijnders, Stefanos Laskaridis, Ali Shahin Shamsabadi +1
Large Language Models (LLM) are typically trained on vast amounts of data from various sources. Even when designed modularly (e.g., Mixture-of-Experts), LLMs can leak privacy on th…