MIT Embodied Intelligence
MIT Embodied Intelligence is a group of labs in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) working in Machine Learning and Robotics. Here you will find videos about our research as well as talks by invited speakers in our seminar.
More information about MIT Embodied Intelligence can be found at https://ei.csail.mit.edu/
Information about accessibility can be found at https://accessibility.mit.edu/
Hao-Wen (Herman) Dong - Towards AI-assisted Video Editing: Generating Shorts from Long Videos
Philip Schroeder - MIT EI Seminar - Recursive Reasoning with LLMs and VLMs
Yung-Sung Chuang - Reducing Hallucinations in LLMs via Decoding, Detection, and Citation
Hongyin Lou - Quantifying Generalization Complexity for Large Language Models
Saurabhchand Bhati - Smaller, Stronger, and Duration-Scalable Audio Learners
Andrew Rouditchenko - Giving Sight to Speech Models
Liming Wang, Can Diffusion Model Disentangle? A Theoretical Perspective
Jehanzeb Mirza, GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
Zhaofeng Wu - The Semantic Hub Hypothesis
Akarsh Kumar - Automating the Search for Artificial Life with Foundation Models
Felix Yanwei Wang - Inference-Time Policy Customization Through Interactive Task Specification
Sharut Gupta - Redefining Context for Powerful Test-Time Adaptation Using Unlabeled Data
EI Seminar - Jason Ma - Recent Progress on Foundation Model Supervision for Robot Learning
EI Seminar - Tim Dettmers - The Promises and Pitfalls of Open-source Agent Systems
EI Seminar - Jaime Fernández Fisac - Games and Filters: A Road to Safe
EI Seminar - Mengzhou Xia - Aligning Language Models with LESS Data and a Simple (SimPO) Objective
EI Seminar - Danny Driess - Have Large Models Changed Robotics?
EI Seminar - Mahi Shafiullah - On Building General, Zero-Shot Robot Policies
EI Seminar - Paul Liang - Foundations of High-Modality Multisensory AI
EI Seminar - Ge Yang - Learning Robust, Real-world Visuomotor Skills from Generated Data
EI Seminar - Naomi Saphra - Interpreting Training
EI Seminar - Jacob Andreas - Good Old-fashioned LLMs (or, Autoformalizing the World)
EI Seminar - Oriol Vinyals - The Deep Learning Toolbox: from AlphaFold to AlphaCode
EI Seminar - Recent papers in Embodied Intelligence I
EI Seminar - Deepak Pathak - Rapid Adaptation in Robot Learning
MIT EI Seminar - Ted Adelson - Good tactile sensing lets robots do cool things
MIT EI Seminar - Pulkit Agrawal - The Task Specification Problem
MIT EI Seminar - Lerrel Pinto - Diverse data and efficient algorithms for robot learning
MIT EI Seminar - Max Welling - Learning equivariant and hybrid message passing on graphs
MIT EI Seminar - Pierre-Yves Oudeyer - Developmental Machine Learning, Curiosity and Deep RL