Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
kyutai 's Collections
Interactivity Alignment
MoshiRAG Release
Hibiki-Zero
Kairos
CASA
ARC-Encoders
Text-To-Speech
Speech-To-Text
Helium 1
MoshiVis v0.1
Hibiki fr-en
Moshi v0.1 Release

Interactivity Alignment

updated about 14 hours ago

Full-duplex speech models post-trained with reinforcement learning for improved conversational interactivity.

Upvote
2

  • Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models

    Paper • 2606.11167 • Published 1 day ago • 1

  • kyutai/moshika-rl-seamless

    Audio-to-Audio • 8B • Updated about 14 hours ago • 3

  • kyutai/personaplex-rl-seamless

    Audio-to-Audio • 8B • Updated about 14 hours ago • 3

  • kyutai/interactivity-alignment-samples

    Viewer • Updated about 14 hours ago • 5.56k • 1.03k • 3
Upvote
2
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs