Kosha Modi
40 posts
@KoshaModified
Logic and poetry. Economist - IMF, Columbia, ISI, Presidency.
Social scientists working with materials requiring digitization can only study what machines can read. In practice, that means printed Latin-script documents from well-funded archives. In a new working paper, I show that Vision Language Models used zero-shot outperform every existing OCR system across every script evaluated, and I propose a pipeline for deploying them on new collections. I apply it to six archival collections spanning 1.8 million pages across six countries for under $1,900.
As usual, it is a pleasure to have an ex MSQE #EconISIDelhi student in my office - @KoshaModified between finishing her PhD from @Univcolumbia and joining the @IMFNews #EconTwitter
Congrats @luchi_casal ! me dicen por interno que te vas de posdoc a Columbia Business, y después al CREI! alto placement! (Lucía fue alumna de nuestra maestría en economía). Y felicitaciones a @juli_caunedo (parece ayer que me contactaste para hablar de Lucía en admissions).
Hi everyone! I am on the job market this year. You can find more about my research here koshamodi.github.io
Hi everyone! I am on the job market this year. You can find more about my research here koshamodi.github.io
In her JMP, Kosha Modi (@koshamodified) addresses the question, “How does the market attribute inflation to demand versus supply sources?”
