I am a fourth-year PhD candidate at Columbia University advised by Carl Vondrick. My research vision is to authentically emulate the varied facets of human behavior in our dynamic world. Concretely, I work on understanding and synthesizing humans by learning 3D representations of human-centric interactions. My research is supported by the Apple Scholars in AI/ML PhD Fellowship, and Columbia Presidential Fellowship.

I completed my Masters in Computer Science from Georgia Tech in 2020 where I was advised by Devi Parikh. During my Masters, I worked on creative AI (see my Masters thesis) and making vision-language models consistent. I also collaborated with Ani Kembhavi at AI2. In 2018, I obtained my Bachelor's Degree in Computer Science from College of Engineering, Pune (COEP) in India.

I have been fortunate to intern at University of Tübingen (2024) with Gerard Pons-Moll, Meta Reality Labs (2023) with Weipeng Xu, UC San Diego (2020) with Xiaolong Wang, and AiBee (2019) with Chunhui Gu. At Columbia, I co-organize the Vision, Interaction, Graphics & Robotics (VIGR) seminar. In my free time, I enjoy listening to and practicing Indian classical music, hiking and playing boardgames.

News

Research

  • How Video Meetings Change Your Expression Sumit Sarin, Utkarsh Mall, Purva Tendulkar, Carl Vondrick
    Paper Project Page Code
    ECCV 2024
  • FLEX: Full-Body Grasping Without Full-Body Grasps Purva Tendulkar, Dídac Surís, Carl Vondrick
    Paper Project Page Talk Code Poster
    CVPR 2023
  • Landscape Learning for Neural Network Inversion Ruoshi Liu, Chengzhi Mao, Purva Tendulkar, Hao Wang, Carl Vondrick
    Paper Blog Post
    ICCV 2023
  • Affective Faces for Goal-Driven Dyadic Communication Scott Geng*, Revant Teotia*, Purva Tendulkar, Sachit Menon, Carl Vondrick
    Paper Project Page
    arXiv 2023
  • Revealing Occlusions with 4D Neural Fields Basile Van Hoorick, Purva Tendulkar, Dídac Surís, Dennis Park, Simon Stent, Carl Vondrick
    Paper Project Page Talk Code
    CVPR 2022 (Oral)
  • SOrT-ing VQA Models: Contrastive Gradient Learning for Improved Consistency Sameer Dharur, Purva Tendulkar, Dhruv Batra, Devi Parikh, Ramprasaath R. Selvaraju
    Paper Talk Code Poster
    NAACL 2021
  • Feel The Music: Automatically Generating A Dance For An Input Song Purva Tendulkar, Abhishek Das, Aniruddha Kembhavi, Devi Parikh
    Paper Talk Code Press Coverage Tech@Meta Article
    ICCC 2020 (Oral)
  • SQuINTing at VQA Models: Interrogating VQA Models with Sub-Questions Ramprasaath R. Selvaraju, Purva Tendulkar, Devi Parikh, Eric Horvitz, Marco Tulio Ribeiro, Besmira Nushi, Ece Kamar
    Paper Talk Dataset
    CVPR 2020 (Oral)
  • Trick or TReAT: Thematic Reinforcement for Artistic Typography Purva Tendulkar, Kalpesh Krishna, Ramprasaath R. Selvaraju, Devi Parikh
    Paper Talk Code
    ICCC 2019 (Oral; Best Presentation Award)

Teaching & Mentorship

Courses
Representation Learning (COMS 6998 - Fall '21, '22)
Teaching Assistant
Columbia University
Mentorship
Women in Science (Fall '21, Spring '22)
Columbia University
BEARS Mentorship (Spring '22)
Barnard College
Amazon-SURE Mentorship (Summer '22)
Amazon & Colubmia University