Tags
99 pages
Daily Publication
LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Better model and token fusion strategy
CAVA: Comprehensive Assessment for Voice Assistants
Focuse on the naunces of speech
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
A clever way to attend to the important region
