Kyutai

non-profit

Verified

https://kyutai.org/

AI & ML interests

None defined yet.

Recent Activity

ameroyer updated a collection 8 days ago

MoshiRAG Release

ameroyer updated a collection 8 days ago

gabrielatkyutail updated a model 14 days ago

kyutai/pocket-tts-without-voice-cloning

View all activity

Papers

One View Is Enough! Monocular Training for In-the-Wild Novel View Generation

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

View all Papers

updated 2 collections 8 days ago

MoshiRAG Release

Candle & PyTorch model checkpoints released as part of the MoshiRAG release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi-rag • 3 items • Updated 8 days ago • 1

Hibiki-Zero

Streaming speech translation without the need for word-level alignments • 4 items • Updated 8 days ago • 2

gabrielatkyutail

updated 2 models 14 days ago

kyutai/pocket-tts-without-voice-cloning

Updated 14 days ago • 8.41k • 24

kyutai/pocket-tts

Updated 14 days ago • 7.53k • 626

updated a model 18 days ago

kyutai/moshi-rag-artifacts

Updated 18 days ago • 1

published a model 18 days ago

kyutai/moshika-rag-pytorch-bf16

Audio-to-Audio • Updated about 1 month ago • 763 • 3

in kyutai/mimi 27 days ago

Is this model can called "VAE" (Varietional AutoEncoder)?

#10 opened 27 days ago by

updated 2 models about 1 month ago

kyutai/moshika-rag-pytorch-bf16

Audio-to-Audio • Updated about 1 month ago • 763 • 3

kyutai/moshika-rag-candle-bf16

Audio-to-Audio • Updated about 1 month ago • 412 • 7

updated a model about 1 month ago

kyutai/ovie

Image-to-Image • Updated Apr 16 • 965 • 12

published a dataset about 1 month ago

kyutai/HaluEvalAudio_1000

Viewer • Updated Apr 15 • 1k • 184

updated a dataset about 1 month ago

kyutai/HaluEvalAudio_1000

Viewer • Updated Apr 15 • 1k • 184

published a model about 1 month ago

kyutai/moshi-rag-artifacts

Updated 18 days ago • 1

updated a model about 1 month ago

kyutai/moshi-rag-artifacts

Updated 18 days ago • 1

published a model about 1 month ago

kyutai/moshika-rag-candle-bf16

Audio-to-Audio • Updated about 1 month ago • 412 • 7

published a model about 2 months ago

kyutai/ovie

Image-to-Image • Updated Apr 16 • 965 • 12

updated a collection about 2 months ago

ARC-Encoders

Pretrained ARC-Encoders and a fine-tuning dataset: context compression for unmodified LLMs. • 6 items • Updated Mar 26 • 4

updated a model about 2 months ago

kyutai/ARC4_Encoder_Llama

Feature Extraction • Updated Mar 26

published a model about 2 months ago

kyutai/ARC4_Encoder_Llama

Feature Extraction • Updated Mar 26

authored a paper about 2 months ago

One View Is Enough! Monocular Training for In-the-Wild Novel View Generation

Paper • 2603.23488 • Published Mar 24 • 5