8 citations · 20 across the 13 of their papers we have counts for
3 papers · 1 filter
A theoretical perspective on mode collapse in variational inference
Roman Soletskyi, Marylou Gabrié, Bruno Loureiro
While deep learning has expanded the possibilities for highly expressive variational families, the practical benefits of these tools for variational inference (VI) are often limite…
Pixtral 12B
Pravesh Agrawal, Szymon Antoniak, Emma Bou Hanna +39
We introduce Pixtral-12B, a 12--billion-parameter multimodal language model. Pixtral-12B is trained to understand both natural images and documents, achieving leading performance o…
Training Safe Neural Networks with Global SDP Bounds
Roman Soletskyi, David "davidad" Dalrymple
This paper presents a novel approach to training neural networks with formal safety guarantees using semidefinite programming (SDP) for verification. Our method focuses on verifyin…