Email: yilundu [at] mit [dot] edu
I am a second-year PhD student at MIT EECS, advised by Prof. Leslie Kaelbling and Prof. Tomas Lozano-Perez and Prof. Josh Tenenbaum. I am interested in learning state representations of the world that enable generalizable long horizon robotic task planning and manipulation given only perceptual observations, in settings where the world is both large and partially observable. My research is driven by the goal of constructing intelligent autonomous household robotics - robots which can accomplish common tasks, such as finding an object or cooking some food, tasks that are trivial for humans, but remain impossible for current AI systems. Previously, I obtained my bachelor's degree from MIT, worked at OpenAI and FAIR, and got a gold medal at the International Biology Olympiad.
- Check out our new preprints on improved training of EBMs and its applications to continual learning!
- State Estimation: long term estimation of the state of mobile objects
- Perception Grounded Manipulation: visually guided multi-step manipulation of object
- Physical and 3D Scene Understanding: unsupervised object discovery, 3D reconstruction
- Generative Modeling: energy-based models, compositionality, applications of generative models
- Reinforcement Learning: multi-agent/model based/unsupervised reinforcement learning