Shanka Subhra Mondal

prof_pic.jpg

Hi! I am a Ph.D. candidate in Electrical and Computer Engineering at Princeton University advised by Jonathan D. Cohen. My research lies at the intersection of machine learning and cognitive neuroscience, taking inspiration from the mechanisms that identify human intelligence and develop neural network models that can demonstrate systematic generalization in abstract reasoning. Last two summers, I interned at Microsoft Research, New York under Ida Momennejad, where I developed a modular and multi-agentic architecture using large language models for improved planning performance. I also worked on a few projects with Sebastian Seung and Tom Griffiths. Before this, I was an undergrad at the Indian Institute of Technology, Kharagpur where I worked with Debdoot Sheet at the intersection of deep learning and biomedical imaging. During my undergrad, I also interned at Adobe Research, Bangalore under Subrata Mitra, where I developed a deep reinforcement learning based scheduler to improve resource utilization and application performance.

selected publications

  1. slot_abstractor_diag_thumbnail.jpg
    Slot Abstractors: Toward Scalable Abstract Visual Reasoning
    Shanka Subhra Mondal, Jonathan D. Cohen, and Taylor W. Webb
    ICML, 2024
  2. ocra.jpg
    Systematic Visual Reasoning through Object-Centric Relational Abstraction
    Shanka Subhra Mondal*, Taylor W. Webb*, and Jonathan D. Cohen
    NeurIPS, 2023
  3. stsn.jpg
    Learning to reason over visual objects
    Shanka Subhra Mondal*, Taylor W. Webb*, and Jonathan D. Cohen
    ICLR, 2023
  4. tvw_rl.jpg
    Scheduling of time-varying workloads using reinforcement learning
    Shanka Subhra Mondal*, Nikhil Sheoran*, and Subrata Mitra
    AAAI, 2021