Your Daily AI Research tl;dr - 2022-09-01 ??

Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.

1?? Faithful Reasoning Using Large Language Models?

"We show how [language models (LMs)] can be made to perform faithful multi-step reasoning via a process whose causal structure mirrors the underlying logical structure of the problem."

Link to the paper: https://arxiv.org/pdf/2208.14271.pdf

2?? MAPTR: STRUCTURED MODELING AND LEARNING FOR ONLINE VECTORIZED HD MAP CONSTRUCTION

A structured end-to-end framework for efficient online vectorized HD map construction (stable and robust map construction in complex and various driving scenes).

Link to the paper: https://arxiv.org/pdf/2208.14437.pdf

3?? [Sponsored] Free Access to the Semantic Layer Summit with 30+ Enterprise Data Leaders

You're invited to a free one-day virtual event. Explore the importance and impact of using a semantic layer for analytics with an all-star lineup of data leaders from Cigna, Starbucks, Bank of America, and more. Lots to look forward to!

Register early to save your free seat

?? DALL·E: Introducing Outpainting

OpenAI just introduced outpainting to DALLE! Outpainting can extend the original image, creating large-scale images in any aspect ratio (see the cover image of this newsletter iteration). It takes into account the image’s existing visual elements to maintain the context of the original?image and can be conditioned with text to add specific elements. Learn more on OpenAI's blog.

Join the discussion with fellow AI professionals on Discord!

Please subscribe and share the newsletter with your AI techy friends if it was helpful and join our 4'000+ readers. Feel free to follow my weekly newsletter where I go in-depth into one of the papers shared, and our newsletter at Towards AI, sharing the most exciting news, papers, articles, and memes weekly.

Thank you for reading,

Louis