102 summarised stories about Multimodal Models, each linking back to the original source. Browse all topics →
GitHub Pages 2 years ago 54
Alibaba released Qwen2-Audio, an updated version of its multimodal AI model that accepts audio and text inputs and generates text outputs. The model builds on Qwen-VL and previous versions of Qwen-Audio to extend the company's large language model capabilities across multiple modalities. This advancement enables users to interact with the AI system using voice input alongside text, expanding the range of input methods for the model.
The daily briefing
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.
TLDRocket
17 October 2026
Microsoft used today’s update to put hard numbers behind the next wave of “base model” ambition. Its MAI-Base-2 is a 2T-parameter foundation model that activates 80B parameters per prompt, trained for 38 days on 16,000 Nvidia GB200 GPUs across 50T tokens. The company says the result is up to 12× more hardware-efficient, and it intends to license the model to “trusted partners” on Azure as a starting point for a new line of LLMs that can be shaped with additional training.
Read the full briefing →