POSS: Position Specialist Generates Better Draft for Speculative Decoding Paper • 2506.03566 • Published Jun 4 • 6
Continuous Visual Autoregressive Generation via Score Maximization Paper • 2505.07812 • Published May 12 • 12
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space Paper • 2505.13181 • Published May 19 • 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 • 16 items • Updated 1 day ago • 241
LLaMA-Omni: Seamless Speech Interaction with Large Language Models Paper • 2409.06666 • Published Sep 10, 2024 • 60