Lychee-FD: The big deal for Full-Duplex Spoken Language Models
Lychee-FD tackles the pesky modality interference in full-duplex SLMs, boosting performance without compromising efficiency. This is a leap forward for speech and NLP.
Read the full articleYou might also wanna read
PersonaPlex: Full-Duplex Voice Without the Fixed Persona
Introduction Voice AI hit a genuine inflection point when full-duplex models arrived. Systems like Moshi finally cracked the core problem wi
Fine-Tuned Small LLMs Outperform Larger Models at 5-30x Lower Cost with Data Curation
Fine-tuned Small LLMs Can Beat Large Ones at 5-30x Lower Cost with Programmatic Data Curation
tensorzero.com·11mo ago
OpenAI launches GPT-Live, a full-duplex voice model for more natural conversations
A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.
openai.com·2d agoOpenAI launches GPT-Live, a full-duplex voice model for more natural conversations
A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.
openai.com·2d agoOpenAI launches GPT-Live, a full-duplex voice model for more natural conversations
A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.
openai.com·2d ago
New Chinese AI models and Liquid Foundation Models push LLM efficiency and reasoning forward
With LLMs increasingly working multimodally, there are exciting developments for more performance and leaner sizes.
heise.de·27d ago
OpenAI launches GPT‑Live voice models with full-duplex conversational capabilities for ChatGPT
OpenAI News: We’re launching GPT‑Live, a new generation of voice models that make talking with AI feel much more like having a real conversa
elevenforum.com·2d ago
Neural Audio Codecs: Bridging the Gap Between Language Models and Audio Processing
Why modeling audio is harder than text, and how to make it feasible with neural audio codecs.
kyutai.org·8mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.