TLDRocket
Sign in

Multimodal Models

102 summarised stories about Multimodal Models, each linking back to the original source. Browse all topics →

+ Follow this topic

Key players

Google MarkTechPost OpenAI Alibaba Hugging Face Mistral

Thursday, 25 January 2024

Introducing Qwen-VL

GitHub Pages 2 years ago 37 ● 2 sources

Alibaba released upgraded versions of its Qwen-VL multimodal model, introducing Qwen-VL-Plus and Qwen-VL-Max with improved image reasoning and text recognition capabilities. The new versions support image resolutions above one million pixels and various aspect ratios, addressing generalization limitations in multimodal AI systems. These upgrades enable better performance on tasks requiring detailed image analysis and text extraction from images.

Read the full story
Multimodal Models Vision-Language Models

The daily briefing

Every AI story that matters, in your inbox by 8am.

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.