Tushaar Gangavarapu
Graduate student (computer science) at Cornell University, Ithaca
Contact: tg352 (at) cornell (dot) edu by email, or G33(D) Gates Hall in person
"[...] But intellectual honesty is more than just acknowledging the work of others and not outsourcing your commencement speech to a neural network. It's also about presenting work in an unbiased manner, about making compelling arguments without misleading, not confusing wanting something to be true really, really badly with it actually being true. [...] There's a fascinating and scientifically very significant instance of intellectual honesty in Newton's understanding of gravity."—Prof. Alyssa Apsel, ECE graduation ceremony, May 2023
I am an MS student at Cornell University (Ithaca), advised by Sasha Rush. I work in the area of efficient language models, more in the context of "how does this component affect model's abilities" (e.g., state space dynamics vs. attention) than hardware optimizations (e.g., flash attention).
I've recently (over the past six-ish months) become increasingly fascinated with the effects of inductive bias in modeling. Specifically, in several languages, including English, it's often noted that "a word is known by the company it keeps!" (distributional hypothesis)–I am currently studying the effects of enabling such biases in language modeling.
I usually enjoy discussions (which is just me learning a lot and having my mind blown!) with Cristian Danescu-Niculescu-Mizil on modeling conversational trajectories, the one-and-only Lillian Lee on everything NLP (and everything interesting!), Sasha Rush on large language models, computational efficiency, and on-going NLP/DL research, and David Bindel on linear algebra (and thought-provoking things such as: would Gauss be shocked if they were brought back to life, in this era!?, and of course about bunnies!).
See my GitHub page for more information on the projects I've recently been working on; you can also check my blog posts to see what I've been focusing on recently (although, I've only started blogging since 08/2023). If you are an undergrad at Cornell and wish to collaborate with me, please email me.
(If you couldn't tell, I spend my free time scouring the internet [= mostly abstrusegoose, handwaving, and xkcd] for math-/CS-related comics!)
Research interests. Large language models, NLP, computational social science
Recognition. For my contributions to CS4740 (and cross-listings) in Fa22, and CS4300 (and cross-listings) in Sp23, I was awarded the Bowers CIS best TA award.
Acknowledgments. Beyond the amazing faculty, my research (and most of my learnings) are in huge part thanks to: Jonathan P. Chang, Lucas Matos Molter, and Sumanth Aluri (THE idiot!). (As Lillian would put it,) my debt to them is unbounded.
Timeline.
| 01/2023–05/2023: | Head TA, Language and Information (CS/INFO4300) Sp24, Cornell University, Ithaca |
| 08/2023–01/2024: | Head TA, Natural Language Processing (CS4740/LING4744/COGST4740/CS5740) Fa23, Cornell University, Ithaca |
| 05/2023–08/2023: | Research intern (advisor: Sasha Rush), Cornell Tech, NYC |
| 01/2023–05/2023: | Head TA, Language and Information (CS4300/INFO4300) sp23, Cornell University, Ithaca |
| 08/2022–01/2023: | Grad TA, Natural Language Processing (CS4740/LING4744/COGST4740/CS5740) fa22, Cornell University, Ithaca |
| 08/2022–now: | Graduate student (major: computer science, minor: applied math), Cornell University, Ithaca |
| 09/2021–08/2022: | Applied scientist, Kindle Content Experience and Quality Algorithms, Amazon |
| 12/2019–09/2021: | Research engineer, Kindle Content Experience and Quality Algorithms, Amazon |
| 06/2019–12/2019: | Software development engineer, worldwide deals, Consumer Engagement, Amazon |
| 08/2018–12/2019: | Scientific researcher at Human-Centered Computing Group and Healthcare Analytics and Language Engineering Lab, NITK Surathkal |
| 05/2018–07/2018: | Software development intern, Kindle Create, Publisher Tools to Reader, Amazon |
| 05/2017–07/2017: | Research intern, Center for Pattern Recognition and Machine Intelligence, PES University |
| 08/2015–04/2019: | Undergraduate student (major: information technology, specialization: aritificial intelligence), NITK Surathkal |
