Sanjiban Choudhury
sanjibanc at cornell dot edu
Assistant Professor
I am an Assistant Professor at Cornell CS and ML Researcher at Aurora.
I work on interactive AI agents that self-align through few-shot interactions with humans and their environment.
My research focuses on reinforcement learning (RLHF), imitation learning (IRL), and foundation models for planning, robotics, and code generation.
I also lead the PoRTaL group. We build everyday robots for everyday users!
News
| Feb 1, 2025 | 4 papers accepted to ICLR 2025! Checkout my paper on Aligning LLM agents, Gonzalo’s LLM planning benchmark, Arnav’s Non-Adversarial IRL, and Nico’s Efficient IRL. |
|---|---|
| Oct 1, 2024 | 2 papers accepted to ICRA 2025, 2 papers at CORL 2024! Checkout our paper on Modular robotics foundation models, Yuki’s Active preference learning with LLMs, Juntao’s Human to Robot Transfer Learning, and Kushal’s One-shot Imitation. |
| Aug 1, 2024 | Thank you OpenAI for the Superalignment Award! Stay tuned for some exciting work on task super alignment, where we use transfer learning to enable generalization from easy to hard tasks. |
| Jul 1, 2024 | Thrilled to receive the ONR Young Investigator award! Excited to explore new ways to teach robots complex, multistep tasks. |
| May 25, 2024 | I got a Google Research Award for Planning with LLMs! Stay tuned for some exciting work on distilling model-based planning into LLMs to solve decision making tasks. |
| May 15, 2024 | MOSAIC: Modular robotics foundation models wins best paper award at VLMN workshop and best poster award at MOMA workshopICRA 2024! |