8 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…
CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding
Gabriel Mahuas, Victoria Shevchenko, Ugo Tanielian +2
Self-supervised pretrained foundation models (FM) have shown early promise for non-invasive electroencephalogram (EEG) decoding applications. Many recent large-scale models converg…
SLAD : Shared LoRA Adapters for Task Specific Distillation
Reda Bensaid, Yassir Bendou, Vincent Gripon +1
In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become increasingly popular. This has…
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…
ReBaPL: Repulsive Bayesian Prompt Learning
Yassir Bendou, Omar Ezzahir, Eduardo Fernandes Montesuma +3
Prompt learning has emerged as an effective technique for fine-tuning large-scale foundation models for downstream tasks. However, conventional prompt learning methods are prone to…
Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation
Eduardo Fernandes Montesuma, Yassir Bendou, Mike Gartrell
Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not…