Kyutai
non-profit
Verified
AI & ML interests
None defined yet.
Recent 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 • 37 • 7 -
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 144 • 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 • 37 • 7 -
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 144 • 2
spaces 5
Running
8
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
6
CALM Samples
🤗
Running
1
Unmute Samples
💻
Examples of conversations with Unmute (unmute.sh)
Running
52
Hibiki Samples
🤗
Translate speech in real-time with high fidelity
models 61
kyutai/pocket-tts-without-voice-cloning
Updated
• 20.3k • 18
kyutai/pocket-tts
Updated
• 44.9k • 511
kyutai/tts-voices
Updated
• 132
kyutai/hibiki-zero-3b-pytorch-bf16
Audio-to-Audio • Updated
• 905 • 40
kyutai/CASA-Qwen2_5-VL-3B-LiveCC
Video-Text-to-Text • 4B • Updated
• 28 • 4
kyutai/Helium1-VL-2B
Image-Text-to-Text • 3B • Updated
• 8 • 1
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text • 3B • Updated
• 37 • 7
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated
• 144 • 2
kyutai/stt-1b-en_fr
Automatic Speech Recognition • Updated
• 117
kyutai/ARC8_Encoder_multi
Feature Extraction • Updated
• 15 • 6
datasets 6
kyutai/Audio-NTREX-4L
Viewer
• Updated
• 3.6k • 320 • 3
kyutai/librispeech_test_clean_enhanced
Viewer
• Updated
• 448 • 211 • 1
kyutai/ARC_finetuning
Preview
• Updated
• 12
kyutai/voices_tts_longeval
Viewer
• Updated
• 1.54k • 17 • 1
kyutai/DailyTalkContiguous
Preview
• Updated
• 11.7k • 19
kyutai/Babillage
Viewer
• Updated
• 465k • 124 • 13