AI Roundup 05/18-> 05/25/2023
A model called DragGAN to manipulate images, Meta's multilingual speech model supporting >1k languages, a ChatGPT-like AI for video editing, and Google's multimodal model to automate web navigation
Microsoft researchers present CoDi, a novel model capable of generating various combinations of output modalities from diverse inputs like video, image, and text (Paper's website)
Researchers from the University of Cambridge present PandaGPT, the first general-purpose multimodal model capable of following instructions across six modalities (Paper's website)
Meta introduces MegaByte, a new architecture that improves Transformer models in both cost and performance by replacing tokens with bytes (Analytics India Magazine)
Google presents a new framework to automate and streamline the code review process using ML (Google AI)
Announcements
Microsoft add native Bing support within ChatGPT, powering it with access to the web including citations and advanced search capabilities (Analytics India Magazine)
Thought-provoking
If you find AI Tidbits valuable, share it with a friend, and consider showing your support.