Rohin Manvi

profile_pic.jpg

I am an incoming CS PhD student at BAIR, advised by Sergey Levine. I am also a researcher at Liquid AI. Previously, I was a CS undergrad (and part coterm) at Stanford, where I had the opportunity to work with Stefano Ermon.

selected publications

  1. adaptive_preview.jpg
    Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
    Rohin Manvi, Anikait Singh, and Stefano Ermon
    2024
  2. bias_preview.jpg
    Large Language Models are Geographically Biased
    Rohin Manvi, Samar Khanna, Marshall Burke, David B. Lobell, and Stefano Ermon
    In Forty-first International Conference on Machine Learning, 2024
  3. geospatial_preview.jpg
    GeoLLM: Extracting Geospatial Knowledge from Large Language Models
    Rohin Manvi, Samar Khanna, Gengchen Mai, Marshall Burke, David B. Lobell, and Stefano Ermon
    In The Twelfth International Conference on Learning Representations, 2024