Amelie Royer

ameroyer's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection about 3 hours ago

MoshiRAG Release

Collection

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 about 3 hours ago • 1

updated a collection about 4 hours ago

Hibiki-Zero

Collection

Streaming speech translation without the need for word-level alignments • 4 items • Updated about 3 hours ago • 2

upvoted 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

New activity in kyutai/CASA-Helium1-VL-2B 2 months ago

Huggingface space?

1

#2 opened 2 months ago by

cakeimaginary5292

updated a Space 2 months ago

Running

Agents

3

CASA Gallery

🏠

3

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

updated a model 2 months ago

kyutai/CASA-Helium1-VL-2B

Image-Text-to-Text • 3B • Updated Mar 9 • 12 • 8

upvoted a paper 4 months ago

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Paper • 2601.10611 • Published Jan 15 • 34

updated a collection 4 months ago

Text-To-Speech

Collection

https://kyutai.org/next/tts • 6 items • Updated Mar 2 • 26

upvoted 2 papers 4 months ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 178

Moshi: a speech-text foundation model for real-time dialogue

Paper • 2410.00037 • Published Sep 17, 2024 • 16

authored 2 papers 5 months ago

Moshi: a speech-text foundation model for real-time dialogue

Paper • 2410.00037 • Published Sep 17, 2024 • 16

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

Paper • 2512.19535 • Published Dec 22, 2025 • 12

upvoted 2 papers 5 months ago

Vision-Speech Models: Teaching Speech Models to Converse about Images

Paper • 2503.15633 • Published Mar 19, 2025 • 2

ARC-Encoder: learning compressed text representations for large language models

Paper • 2510.20535 • Published Oct 23, 2025 • 8

updated 5 collections 5 months ago

Moshi v0.1 Release

Collection

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 16 items • Updated Dec 24, 2025 • 244

Hibiki fr-en

Collection

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 7 items • Updated Dec 24, 2025 • 55

ARC-Encoders

Collection

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

CASA

Collection

CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion on long-context streaming inputs • 6 items • Updated Mar 9 • 7

MoshiVis v0.1

Collection

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 6 items • Updated Mar 2 • 23