5 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…
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…
Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise
Steve Hong, Samuel Belkadi
We reinterpret Visual Autoregressive (VAR) models as iterative refinement models to identify which design choices drive their quality-efficiency trade-off. Instead of treating VAR…
Diffusion-Free Graph Generation with Next-Scale Prediction
Samuel Belkadi, Steve Hong, Marian Chen +3
Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such a…
Generating Synthetic Free-text Medical Records with Low Re-identification Risk using Masked Language Modeling
Samuel Belkadi, Libo Ren, Nicolo Micheletti +2
The vast amount of available medical records has the potential to improve healthcare and biomedical research. However, privacy restrictions make these data accessible for internal…