analiza aiqbench
Liquid AI has introduced two open-weight models, d1-3B and d1-omni-600M, designed specifically for real-time decision-making rather than text generation. These multimodal architectures process inputs like text, images, or audio to return calibrated answers in a single forward pass without producing output tokens. This approach shifts the focus from traditional generative capabilities to efficient, low-latency inference suitable for autonomous systems and robotics.
Liquid AI Releases Open-Weight d1-3B and d1-omni-600M: Multimodal Decision Models With Zero Output Tokens
Liquid AI has released Open d1, two open-weight multimodal models in its d1 decision model family. d1-3B reads text and images. d1-omni-600M reads text with an image, or text with audio. Neither model writes text. Each returns calibrated, typed answers in one forward pass with zero output tokens. The target is real-time decisions on the […] The post Liquid AI Releases Open-Weight d1-3B and d1-omni-600M: Multimodal Decision Models With Zero Output Tokens appeared first on MarkTechPost.
Citește articolul complet pe MarkTechPostSubiecte conexe
Multimodal open d1 decision models for the edge
Hugging Face · 7 oct. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
[AINews] Quasi-Riemann-Hypothesis: OpenAI publishes 722 math papers solving 90 of the top 500 open math problems; “the most significant moment” in >100 years of mathematics
Latent Space · 7 oct. 2026
[AINews] High Taste Testers Ep. 1
Latent Space · 17 oct. 2026