About me
Hi! I am a second-year PhD student in the GLAMOR Lab at University of Southern California, where I am working with Prof. Jesse Thomason on language grounding in perception and, more broadly, the world. I am also currently doing a summer internship at AI2 Mosaic, where I am working with Jack Hessel and Khyathi Chandu on vision-language reasoning.
Before this, I was a Research Intern at Microsoft Research, and briefly worked as an NLP Research Scientist at AI Foundation. I completed my Masters from the Language Technologies Institute at Carnegie Mellon University, where I had the pleasure of working with Prof. Yonatan Bisk, Prof. Louis-Philippe Morency and Prof. Florian Metze.
My research interests lie in the area of multimodal machine learning and language grounding. My Master’s research revolved around using vision to make speech recognition models more robust to missing/noisy audio signal. I have also recently worked on other NLP applications such as dialog, machine translation and computational social science.
Prior to CMU, I graduated from the Indian Institute of Technology, Bombay, majoring in Mechanical Engineering, with a Minor degree in Computer Science.
News
- May 2023: One paper accepted to Interspeech 2023!
- May 2023: One paper accepted to CoLLAs 2023!
- May 2023: Started my summer internship at AI2 Mosaic!
- May 2023: Incredibly grateful to have received the Viterbi Undergraduate Research Mentoring Award!
- April 2023: Curriculum Learning for Data-Efficient Vision-Language Alignment will be presented at the O-DRUM workshop at CVPR 2023!
- Feb 2023: I will be doing a research internship at AI2 Mosaic this summer!
- Oct 2022: Gave invited talks on CLiMB at the Montréal Institute of Learning Algorithms and the ContinualAI Seminar - slides and video.
- Sept 2022: CLiMB 🧗♂️ was accepted to the NeurIPS 2022 Datasets and Benchmarks Track! See you in New Orleans ⚜️🎷!
- Aug 2022: New pre-print! in Curriculum Learning for Data-Efficient Vision-Language Alignment, we align pre-trained image and text encoders to get comparable retrieval performance to CLIP, with < 1% of the data!
- June 2022: Pre-print alert! We introduce CLiMB 🧗♂️, a new continual learning benchmark for vision-and-language tasks.
- May 2022: Our paper Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models got accept to the Gender Bias in NLP workshop at NAACL 2022!
- Aug 2021: Moved to LA and started my PhD at USC - excited to spend the next few years at the GLAMOR Lab! ✨
- April 2021: New pre-print alert!
- March 2021: I will be joining University of Southern California for my PhD, working on language grounding with Jesse Thomason!
- Oct 2020: Two papers accepted to the Workshop on NLP Beyond Text at EMNLP 2020 :)
- Sept 2020: Our paper on Fine-Grained Grounding for Multimodal Speech Recognition has been accepted to Findings of EMNLP 2020!
- July 2020: I will be joining AI Foundation as a Research Scientist in September, working on dialog :)
- Jan 2020: Our paper on multimodal ASR, Looking Enhances Listening (LEL), has been accepted to ICASSP 2020! See you
in Barcelona :)on zoom :( - Oct 2019: Our paper got accepted to IWSLT 2019!
- Sept 2019: Our work on Structured Fusion Networks for Dialog was awarded the Best Paper Award at SIGDIAL 2019!