Abstract: Multi-modal and cross-modal retrieval has garnered increasing attention from researchers recently, owing to its potential to transcend the limitations imposed by traditional retrieval ...

Finally, the code for the web UI client used in the Moshi demo is provided in the client/ directory. If you want to fine tune Moshi, head out to kyutai-labs/moshi ...

As the title suggests and in order to keep the world a safe place for living, this is again going to be entirely virtual face-to-face meeting. We will work in 45-minute shifts, with a 15-minute break, ...