POSS: Position Specialist Generates Better Draft for Speculative Decoding Paper • 2506.03566 • Published 7 days ago • 6
Continuous Visual Autoregressive Generation via Score Maximization Paper • 2505.07812 • Published 29 days ago • 12
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space Paper • 2505.13181 • Published 23 days ago • 9
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 • 15 items • Updated Apr 18 • 231
LLaMA-Omni: Seamless Speech Interaction with Large Language Models Paper • 2409.06666 • Published Sep 10, 2024 • 58