Kyutai

non-profit

Verified

https://kyutai.org/

AI & ML interests

None defined yet.

Recent Activity

gabrielatkyutail updated a model about 20 hours ago

kyutai/pocket-tts-without-voice-cloning

gabrielatkyutail updated a model about 21 hours ago

kyutai/pocket-tts

ming024 updated a model 1 day ago

kyutai/moshika-rag-candle-bf16

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

gabrielatkyutail

updated a model about 20 hours ago

kyutai/pocket-tts-without-voice-cloning

Updated about 20 hours ago • 25.1k • 22

gabrielatkyutail

updated a model about 21 hours ago

kyutai/pocket-tts

Updated about 20 hours ago • 15k • 595

updated a model 1 day ago

kyutai/moshika-rag-candle-bf16

Audio-to-Audio • Updated 1 day ago • 67 • 3

updated a model 2 days ago

kyutai/ovie

Image-to-Image • Updated 2 days ago • 306 • 7

published a dataset 3 days ago

kyutai/HaluEvalAudio_1000

Viewer • Updated 3 days ago • 1k • 43

updated a dataset 3 days ago

kyutai/HaluEvalAudio_1000

Viewer • Updated 3 days ago • 1k • 43

published a model 3 days ago

kyutai/moshi-rag-artifacts

Updated 3 days ago • 1

updated a model 3 days ago

kyutai/moshi-rag-artifacts

Updated 3 days ago • 1

published a model 5 days ago

kyutai/moshika-rag-candle-bf16

Audio-to-Audio • Updated 1 day ago • 67 • 3

published a model 16 days ago

kyutai/ovie

Image-to-Image • Updated 2 days ago • 306 • 7

updated a collection 23 days ago

ARC-Encoders

Pretrained ARC-Encoders and a fine-tuning dataset: context compression for unmodified LLMs. • 6 items • Updated 23 days ago • 4

updated a model 23 days ago

kyutai/ARC4_Encoder_Llama

Feature Extraction • Updated 23 days ago

published a model 23 days ago

kyutai/ARC4_Encoder_Llama

Feature Extraction • Updated 23 days ago

authored a paper 23 days ago

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

Paper • 2603.23488 • Published 25 days ago • 5

submitted a paper to Daily Papers 24 days ago

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

Paper • 2603.23488 • Published 25 days ago • 5

gabrielatkyutail

in kyutai/stt-2.6b-en-trfs about 1 month ago

Update README.md

#2 opened about 1 month ago by

in kyutai/CASA-Helium1-VL-2B about 1 month ago

Huggingface space?

#2 opened about 1 month ago by

cakeimaginary5292

updated a model about 1 month ago

kyutai/tts-voices

Updated Mar 9 • 143

updated a Space about 1 month ago

CASA Gallery

Video Gallery for CASA: Cross-Attention over Self-Attention

updated a model about 1 month ago

kyutai/CASA-Helium1-VL-2B

Image-Text-to-Text • 3B • Updated Mar 9 • 10 • 8