Kyutai
non-profit
Verified
AI & ML interests
None defined yet.
Recent Activity
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
CASA: Cross-Attention as Self-Attention for Efficient Vision-Language Fusion on long context streaming inputs
-
CASA Gallery
🏠2Video Gallery for CASA: Cross-Attention via Self-Attention
-
CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
Paper • 2512.19535 • Published • 12 -
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 59 • 7 -
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 263 • 2
CASA: Cross-Attention as Self-Attention for Efficient Vision-Language Fusion on long context streaming inputs
-
CASA Gallery
🏠2Video Gallery for CASA: Cross-Attention via Self-Attention
-
CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
Paper • 2512.19535 • Published • 12 -
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 59 • 7 -
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 263 • 2
spaces
5
Running
Hibiki Zero Samples
🏆
Demo samples of the speech translation model Hibiki-Zero.
Running
2
CASA Gallery
🏠
Video Gallery for CASA: Cross-Attention via Self-Attention
Running
5
CALM Samples
🤗
Running
1
Unmute Samples
💻
Examples of conversations with Unmute (unmute.sh)
Running
51
Hibiki Samples
🤗
Translate speech in real-time with high fidelity
models
61
kyutai/hibiki-zero-3b-pytorch-bf16
Audio-to-Audio
•
Updated
•
163
•
1
kyutai/tts-voices
Updated
•
127
kyutai/pocket-tts
Updated
•
62.8k
•
540
kyutai/pocket-tts-without-voice-cloning
Text-to-Speech
•
Updated
•
87.8k
•
14
kyutai/CASA-Qwen2_5-VL-3B-LiveCC
Video-Text-to-Text
•
4B
•
Updated
•
54
•
4
kyutai/Helium1-VL-2B
Image-Text-to-Text
•
3B
•
Updated
•
37
•
1
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text
•
3B
•
Updated
•
59
•
7
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text
•
4B
•
Updated
•
263
•
2
kyutai/stt-1b-en_fr
Automatic Speech Recognition
•
Updated
•
114
kyutai/ARC8_Encoder_multi
Feature Extraction
•
Updated
•
18
•
6
datasets
6
kyutai/Audio-NTREX-4L
Updated
•
33
kyutai/librispeech_test_clean_enhanced
Viewer
•
Updated
•
448
•
561
•
1
kyutai/ARC_finetuning
Preview
•
Updated
•
8
kyutai/voices_tts_longeval
Viewer
•
Updated
•
1.54k
•
19
•
1
kyutai/DailyTalkContiguous
Preview
•
Updated
•
970
•
19
kyutai/Babillage
Viewer
•
Updated
•
465k
•
118
•
13