11 papers
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273
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…
Jais 2: A Family of Arabic-Centric Open Large Language Models
Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim +57
Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong p…
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Abdelaziz Bounhar, Rania Hossam Elmohamady Elbadry, Hadi Abdine +3
Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-…
Distributed Detection under Stringent Resource Constraints
Abdelaziz Bounhar, Mireille Sarkiss, Michèle Wigger
This paper identifies the Stein-exponent of distributed detection when the sensor communicates to the decision center over a discrete memoryless channel (DMC) subject to one of thr…
Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
Abdelaziz Bounhar, Hadi Abdine, Evan Dufraisse +5
Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (R…
Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts
Guokan Shang, Hadi Abdine, Ahmad Chamma +7
We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts…
Whispering Secrets in a Crowd: Leveraging Non-Covert Users for Covert Communications
Abdelaziz Bounhar, Mireille Sarkiss, Michèle Wigger
This paper establishes the fundamental limits of a multi-access system where multiple users communicate to a legitimate receiver in presence of an external warden. Only a specific…
Unveiling Covert Semantics: Joint Source-Channel Coding Under a Covertness Constraint
Abdelaziz Bounhar, Mireille Sarkiss, Michèle Wigger
The fundamental limit of Semantic Communications (joint source-channel coding) is established when the transmission needs to be kept covert from an external warden. We derive infor…
Covert Multi-Access Communication with a Non-Covert User
Abdelaziz Bounhar, Mireille Sarkiss, Michèle Wigger
In this paper, we characterize the fundamental limits of a communication system with three users (i.e., three transmitters) and a single receiver where communication from two cover…
Mixing a Covert and a Non-Covert User
Abdelaziz Bounhar, Mireille Sarkiss, Michèle Wigger
This paper establishes the fundamental limits of a two-user single-receiver system where communication from User 1 (but not from User 2) needs to be undetectable to an external war…