Sanjana Srivastava

Computer Science PhD Student at Stanford University

Stanford, California, United States

About

Graduating Stanford AI PhD student interested in evaluation and RL-based adaptation of large models. I use natural human data as evaluation, rubric, and reward signal for complex model behaviors. Interested in robotic foundation models that enable both dexterity and cross-task generalization to the point of interacting meaningfully with human needs. Check out: - BEHAVIOR: large-scale structured evaluation for embodied AI (https://behavior.stanford.edu/) - ROSETTA: RL reward generation from natural language (sanjanasrivastava.github.io/rosetta-project/) - Offline RL from binary preference, with DeepMind Interactive Agents (https://arxiv.org/pdf/2211.11602)

Experience

  • Senior AI Researcher at Together AI
    Oct 2025 - Present · 10 mos

  • PhD Student/Graduate Research Assistant at Stanford University
    Sep 2019 - Jun 2025 · 5 yrs 10 mos

  • Research Scientist Intern at Google DeepMind
    Jun 2022 - Oct 2022 · 5 mos

    - Developed imitation and reinforcement learning-based agent for virtual agent in physics-simulated 3D Playhouse environment - Applied offline RL methods established in MuZero to Playhouse agent - Worked with Bradley-Terry binary preference-based reward models in offline RL pipeline

  • Graduate Research Assistant at McGovern Institute for Brain Research at MIT
    Oct 2015 - May 2019 · 3 yrs 8 mos

    Investigated failure modes of convolutional neural networks (CNNs) in object recognition tasks; established similarities and differences between object recognition models and human visual recognition ability; added human model of visual attention to CNN to reduce required training data and improve performance.

  • Data Science Intern at Facebook
    Jun 2017 - Aug 2017 · 3 mos