Done at Meta Reality Labs Research in colloaboration with FAIR, in this work we consider the important complementary problem of inferring that goal from multi-modal contextual observations. Solving this “goal inference” problem holds the promise of eliminating the effort needed to interact with such an agent. This work focuses on creating WAGIBench, a strong benchmark to measure progress in solving this problem using vision-language models (VLMs)

This is a simple mortgage calculator I created, because the visualization was essential for me to comprehend my own mortgage over time. My hope is that it is helpful to someone else who has similar needs. I had multiple notebooks simulating various paydown scenarios, so I also created the project as a means to make the analysis and shareability more robust.