Samar Khanna

Founding ML Research @ Stealth | MS CS @ Stanford | CS @ Cornell

samar_khanna.jpg

I am a founding ML/research engineer at a stealth startup led by Stanford Prof. Stefano Ermon, building next-generation large language models.

Recently, I received my MS in CS with a distinction in research from Stanford University, specializing in AI. I worked with Prof. Stefano Ermon on self-supervised learning, generative (diffusion) models, and on building foundation models for geospatial tasks. My research interests center on making ML models generalize effectively to new, real-world data, especially to solve societally relevant tasks such as sustainability.

Before Stanford, I completed my Bachelor’s in CS at Cornell University, where I did research with Dean Kavita Bala and Prof. Bharath Hariharan. I was also actively involved as a team-lead in Cornell Data Science, a student-run project team.

Professionally, I have worked at Aurora as an ML engineer and have completed ML internships at NVIDIA and at Uber ATG.

For fun, I swim and play tennis– to relax, I enjoy reading books and watching movies.


Announcements

Sep 2024 I left Aurora and joined Prof. Ermon to build next-generation, non-autoregressive LLMs at our new startup! Stay tuned for updates!
Jun 2023 I graduated from Stanford!
May 2021 4 years of Cornell all wrapped up…

Selected Publications

  1. explora_teaser.png
    ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
    Samar Khanna, Medhanie Irgau, David B. Lobell, and Stefano Ermon
    arXiv preprint arXiv:2406.10973, 2024
  2. diffusion_sat_main.png
    DiffusionSat: A Generative Foundation Model for Satellite Imagery
    Samar Khanna, Patrick Liu, Linqi Zhou, Chenlin Meng, Robin Rombach, Marshall Burke, David B. Lobell, and Stefano Ermon
    In The Twelfth International Conference on Learning Representations , 2024
  3. sat_mae.png
    SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery
    Samar Khanna*, Yezhen Cong*, Chenlin Meng, Patrick Liu, Erik Rozi, Yutong He, Marshall Burke, David B. Lobell, and Stefano Ermon
    In Advances in Neural Information Processing Systems , 2022
  4. llm_bias.jpeg
    Large Language Models are Geographically Biased
    Rohin Manvi, Samar Khanna, Marshall Burke, David Lobell, and Stefano Ermon
    In Forty-first International Conference on Machine Learning , 2024
  5. ddbm.png
    Denoising Diffusion Bridge Models
    Linqi Zhou, Aaron Lou, Samar Khanna, and Stefano Ermon
    In The Twelfth International Conference on Learning Representations , 2024