Nimit Kalra

Howdy! I'm a writer with a quant finance day job.

During my undergrad career at UT Austin, I worked with Philipp Krähenbühl on computer vision and robotics research. I left with a BA in Math, a BS in Computer Science, and a bunch of credits in Political Science/Economics.

As a high-school student, I led development of some popular open-source software — n, Git Goodies, git-fire, and git-extras — and directed CodeDay and HackDFW.

Essays

Intelligence in the Interior — June 2022

Somewhere between Houston and Chambers, an older couple asked us if we were students. It didn’t matter to him what my politics actually were. As long as he could assume that I was as he thought I would be. That smart and just people voted the way he did — thereby making him smart and just by association.

A Question for Cory Booker (D-NJ) — June 2022

I had the opportunity to ask — "Some of the most beautiful and compelling ideas that we cherish in our nation today were at one point quite controversial and unpopular. As you mentioned, the Civil Rights movement was not a result of Senators in suits deciding to grant rights — it was the hard work of passionate citizens who convinced a nation with their ideas. And yet, there was a time when a majority would’ve surely preferred to censor such ideas. What do you see as the future of social media regulation and how can we protect free debate online?"

21st Century Guard Labor — April 2022

It is fitting that being a "webmaster" requires no special certification or inclusion in some privileged class. Any script-kiddie from around the world can give a blog post the appearance of credibility by spoofing a publish date or changing the look-and-feel to match an academic article. Perhaps this is why the digital world is so hated by those who uphold a class system.

Publications

Domain Adaptation Through Task Distillation
European Conference on Computer Vision, 2020
Brady Zhou*, Nimit Kalra*, Philipp Krähenbühl
[arXiv]   [code]   [presentation]

Domain adaptation framework for transferring tasks between visually-diverse domains. We successfully transfer agents that navigate mazes and race karts to drive autonomously in a photorealistic simulator.

Projects

[report]   Statement of Purpose for Computer Science Ph.D. Programs

[report]   Domain Adaptation Through Multi-Task Distillation via Noisy-Labels

[report]   A Bayesian Network Model for Sampling Dockless Scooter Traffic

[report]   [code]   Fast Random Kernelized Features: High-Dimensional SVM Classification

[report]   [slides]   Composition of Real Flows

Contact

I enjoy meeting new people. Feel free to reach me at nimit@utexas.edu or schedule a chat.