people
members of the lab or group
555 your office number
123 your address street
Your City, State 12345
layout: about title: about permalink: / subtitle:
profile: align: right image: prof_pic-2.jpg image_circular: false # crops the image to make it circular
news: true # includes a list of news items selected_papers: true # includes a list of papers marked as “selected={true}” social: true # includes social icons at the bottom of the page —
Hi! I’m Siddharth, a student at Carnegie Mellon University completing my Fifth-Year Master’s in Computer Science. My thesis focuses on mechanistic interpretability - specifically, uncovering the internal circuits and representation geometry that LLMs use to parse and reason over tabular data.
As a part of Professor Carolyn Rosé’s group at CMU’s Language Technologies Institute - I collaborated with Armineh Nourbakhsh on developing graph-based models for form processing, and robust evaluation metrics for document visual question answering.
I am also fascinated by the intersection of game theory and AI — particularly, how optimal play emerges in complex environments. I find that viewing deep learning through this lens: as players discovering complex strategies in a massive game, makes for a compelling perspective driving my interpretability research.
Feel free to reach out to me to chat about my research or any shared interests!
555 your office number
123 your address street
Your City, State 12345
layout: about title: about permalink: / subtitle:
profile: align: right image: prof_pic-2.jpg image_circular: false # crops the image to make it circular
news: true # includes a list of news items selected_papers: true # includes a list of papers marked as “selected={true}” social: true # includes social icons at the bottom of the page —
Hi! I’m Siddharth, a student at Carnegie Mellon University completing my Fifth-Year Master’s in Computer Science. My thesis focuses on mechanistic interpretability - specifically, uncovering the internal circuits and representation geometry that LLMs use to parse and reason over tabular data.
As a part of Professor Carolyn Rosé’s group at CMU’s Language Technologies Institute - I collaborated with Armineh Nourbakhsh on developing graph-based models for form processing, and robust evaluation metrics for document visual question answering.
I am also fascinated by the intersection of game theory and AI — particularly, how optimal play emerges in complex environments. I find that viewing deep learning through this lens: as players discovering complex strategies in a massive game, makes for a compelling perspective driving my interpretability research.
Feel free to reach out to me to chat about my research or any shared interests!