4 papers
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…
MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
Mircea LicÄ, Ojas Shirekar, Baptiste Colle +1
Embodied agents powered by large language models (LLMs), such as Voyager, promise open-ended competence in worlds such as Minecraft. However, when powered by open-weight LLMs they…
Masked Generative Priors Improve World Models Sequence Modelling Capabilities
Cristian Meo, Mircea Lica, Zarif Ikram +6
Deep Reinforcement Learning (RL) has become the leading approach for creating artificial agents in complex environments. Model-based approaches, which are RL methods with world mod…
Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases
Cristian Meo, Akihiro Nakano, Mircea LicÄ +7
Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as pre…