Suvansh Sanjeev

I am a third-year PhD student on leave from the Robotics Institute at Carnegie Mellon University, where I am advised by Zico Kolter and Zac Manchester. I am interested in safe AI and large language models. I graduated from UC Berkeley, where I worked with Professors Sergey Levine and Claire Tomlin in the Berkeley Artificial Intelligence Research (BAIR) Lab on deep RL and safe learning.

 /   /   /   / 

profile photo

I am currently working on Brilliantly, making open-source AI projects and providing custom AI solutions for clients. Learn more about the projects Brilliantly is working on here. Most recently, we launched Blitz, a demo chatbot that allows users to converse with numerical data, rather than text.

My past research worked towards bringing reinforcement learning to the real world. Most recently, I worked on gray-box methods for control of quadrotors. I have also worked on developing more natural means of task specification for deep RL to avoid the burden of manually engineered reward functions, as well as on developing data-efficient learning techniques that allow for safety guarantees throughout the learning process.

blitz Blitz: Chat with NFL Stats
Suvansh Sanjeev

autoplugin AutoPlugin: Generate ChatGPT Plugins from Python Code
Suvansh Sanjeev

[Blog] [Code]
say anything Say Anything: Natural Language Prompting for Meta's Segment Anything Model
Suvansh Sanjeev

[Blog] [Extension Code] [Backend Code]
sightbot SightBot: ChatGPT-Powered Research Insights with PubMed Citations
Suvansh Sanjeev

[Blog] [Backend Code] [ Frontend Code]
quadrotor thesis Learning Parameter-Efficient Markovian Quadrotor Dynamics Models
Suvansh Sanjeev
CMU Masters Thesis, 2022
safe learning Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability
Sylvia Herbert*, Jason J. Choi*, Suvansh Sanjeev, Marsalis Gibson, Koushil Sreenath, Claire J. Tomlin
Robotics: Science and Systems, 2021
pave PaVE the Way for NFL Passing Analytics: Passing Value in Expectation
NFL Big Data Bowl 2021
ecological RL Ecological Reinforcement Learning
John D. Co-Reyes*, Suvansh Sanjeev*, Glen Berseth, Abhishek Gupta, Sergey Levine
Deep RL Workshop at NeurIPS, 2019
clean-usnob Guiding Policies with Language via Meta-Learning
John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, Jacob Andreas, John DeNero, Pieter Abbeel, Sergey Levine
International Conference on Learning Representations, 2019
Best Paper at Meta-Learning Workshop at NeurIPS, 2018

I received the 2020-2021 Outstanding Graduate Student Instructor Award at UC Berkeley, where I was fortunate enough to serve as the head teaching assistant for the incredible Professors Gireeja Ranade, Alexandre Bayen, and Babak Ayazifar.

One of three lectures I delivered during the Fall 2019 offering of EECS 127/227A can be found here.

clean-usnob EECS 127 (Convex Optimization), Spring 2019, Fall 2019 (Head TA)

EE 120 (Signals and Systems), Fall 2018 (Head TA)

CS 61C (Great Ideas in Computer Architecture (Machine Structures), Summer 2018

Website template