Amita Kamath

I am a third-year PhD candidate fortunate to be co-advised by Kai-Wei Chang at UCLA and Ranjay Krishna at UW. I frequently collaborate with the Allen Institute for AI (AI2) as well!

Previously, I was a Pre-doctoral Young Investigator (PYI) at AI2, where I worked with the PRIOR team on general purpose vision-language systems. Before that, I completed my MS in the Computer Science department at Stanford University, where I worked with Percy Liang's group on distribution shift in NLP.

Here is my CV!

Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning Amita Kamath, Jack Hessel, Khyathi Chandu, Jena Hwang, Kai-Wei Chang, Ranjay Krishna under submission [PDF]

Matryoshka Query Transformer for Large Vision-Language Models Wenbo Hu, Zi-Yi Dou, Liunian Harold Li, Amita Kamath, Nanyun Peng, Kai-Wei Chang NeurIPS 2024 [PDF]

The Hard Positive Truth about Vision-Language Compositionality Amita Kamath, Cheng-Yu Hsieh, Kai-Wei Chang, Ranjay Krishna ECCV 2024 [PDF] [slides]

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models Adyasha Maharana, Amita Kamath, Christopher Clark, Mohit Bansal, Aniruddha Kembhavi TMLR 2024 [PDF]

Text encoders bottleneck compositionality in contrastive vision-language models Amita Kamath, Jack Hessel, Kai-Wei Chang EMNLP 2023 [PDF]

What's "up" with vision-language models? Investigating their struggle with spatial reasoning Amita Kamath, Jack Hessel, Kai-Wei Chang EMNLP 2023 [PDF]

Webly Supervised Concept Expansion for General Purpose Vision Models Amita Kamath*, Christopher Clark*, Tanmay Gupta*, Eric Kolve, Derek Hoiem, Aniruddha Kembhavi ECCV 2022 [PDF] [webpage]

Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture Tanmay Gupta, Amita Kamath, Aniruddha Kembhavi, Derek Hoiem CVPR 2022 (Oral) [PDF] [webpage]

Selective Question Answering under Domain Shift Amita Kamath, Robin Jia, Percy Liang ACL 2020 [PDF] [Codalab]

Selective Prediction under Domain Shift for Question Answering Amita Kamath, Robin Jia, Percy Liang Master's Thesis [PDF]

ARTINALI: Dynamic Invariant Detection for Cyber-Physical System Security [Undergraduate] Maryam Aliabadi, Amita Kamath, Julien Gascon-Samson, Karthik Pattabiraman FSE 2017 [PDF]

• In Summer 2019, I was the Head TA for CS221 (Artificial Intelligence), taught by Robin Jia. I managed a team of 6 TAs and over 100 students, taught sections, and mentored several student project teams.
• In Winter 2020, I was a TA for CS224n (Natural Language Processing with Deep Learning), taught by Chris Manning. I worked with a team of 23 TAs and over 450 students, and mentored several student project teams.
• In Winter 2019, I was a TA for CS224n (Natural Language Processing with Deep Learning), taught by Chris Manning. I worked with a team of 20 TAs and over 400 students, helped develop new assignments, and mentored several student project teams.
• In Autumn 2018, I was a TA for CS221 (Artificial Intelligence), taught by Percy Liang. I worked with a team of 15 TAs and over 400 students, and mentored several student project teams.

• Student Member of the Stanford MSCS Admissions Committee, 2019.
• Organizer of the weekly Stanford NLP Reading Group, Fall 2019.

• Graduate Dean's Scholar Award, UCLA 2022-24.
• CS Department First-Year Fellowship, UCLA 2022-23.
• Top 3 Projects Award, CS224n (NLP with Deep Learning) 2018.
• Mitacs Globalink Research Fellowship, 2016.
• Indian Academies of Science Summer Research Fellowship, 2015.
• Highest GPA awards, Computer Science Department, NITK, 2015-17.