Kyutai

non-profit

Verified

https://kyutai.org/

kyutai_labs

kyutai-labs

AI & ML interests

None defined yet.

Recent Activity

ameroyer authored a paper 7 days ago

Moshi: a speech-text foundation model for real-time dialogue

ameroyer authored a paper 7 days ago

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

ameroyer updated a collection 9 days ago

Moshi v0.1 Release

View all activity

Papers

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

ARC-Encoder: learning compressed text representations for large language models

View all Papers

kyutai 's Papers 4

Submitted by

Niels Rogge

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

kyutai

Submitted by

Hippolyte Pilchen

ARC-Encoder: learning compressed text representations for large language models

kyutai

Vision-Speech Models: Teaching Speech Models to Converse about Images

kyutai

Moshi: a speech-text foundation model for real-time dialogue

kyutai