Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images.<a href="https://www.microsoft.com/en-us/research/publication/mathvista-evaluating-mathematical-reasoning-of-foundation-models-in-visual-contexts/">Read the paper</a><a href="https://mathvista.github.io/">Get the code & dataset</a>

Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images. Read the paper Get the code & dataset

Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images.<a href="https://www.microsoft.com/en-us/research/publication/mathvista-evaluating-mathematical-reasoning-of-foundation-models-in-visual-contexts/" rel="noopener noreferrer">Read the paper</a><a href="https://mathvista.github.io/" rel="noopener noreferrer">Get the code &amp; dataset</a>

Abstracts: May 6, 2024

An ongoing series of conversations bringing you right up to the cutting edge of Microsoft Research.

Share Abstracts: May 6, 2024

Sign up to save your podcasts

Abstracts: May 6, 2024

Abstracts: May 6, 2024

More shows like Microsoft Research Podcast

The Daily

Dwarkesh Podcast

Hard Fork

No Priors: Artificial Intelligence | Technology | Startups