Computer Science and Artificial Intelligence Laboratory (CSAIL)

clear all
A diagram of wireless signals emanating from a small device mounted on a wall. The wireless signal expands to encompass a person walking with a shuffling gait.
September 22, 2022

In-home wireless device tracks disease progression in Parkinson’s patients

By continuously monitoring a patient’s gait speed, the system can assess the condition’s severity between visits to the doctor’s office.

September 13, 2022

Collaborative machine learning that preserves privacy

Researchers increase the accuracy and efficiency of a machine-learning method that safeguards user data.

September 13, 2022

AI system makes models like DALL-E 2 more creative

Researchers develop a new method that uses multiple models to create more complex images with better understanding.

Doctoral Thesis: Effective Modeling in Medical Imaging with Constrained Data

Tzu-Ming Harry Hsu Abstract: Data for modern medical imaging modeling is constrained by their high physical density, complex structure, insufficient annotation, heterogeneity across sites, long-tailed distribution, and sparsely

Doctoral Thesis: Towards Computational Design of Shape and Control for Rigid Robots

Jie Xu Abstract: Designing a performing robotic system for given tasks is traditionally labor-intensive for finding the optimal configurations of its hardware shape and/or software controller. The underlying

Doctoral Thesis: Passive Health Monitoring with Radio Waves — In Body and In Home

Guo Zhang Abstract: Current health care is primarily in-clinic, episodic, and semi-empirical. With the development of intelligent devices such as smartphones, smartwatches, and more cutting-edge devices such as

Doctoral Thesis: Learning inside the prediction function

Ferran Alet Abstract: Many of the achievements in machine learning have followed different variations on a single recipe: we pick a supervised training dataset and assume there exists

Doctoral Thesis: Autonomous Navigation without HD Prior Maps

Teddy Ort Abstract:Most fielded autonomous driving systems currently rely on High Definition (HD) prior maps both to localize, and to retrieve detailed geometric and semantic information about the

Doctoral Thesis: Empowering K-12 students in understanding and designing conversational agents

Jessica Van Brummelen Abstract: Interacting with technology through conversation has rapidly become prominent, and raises unique questions, including, “How do such human-like, relational interactions affect people’s trust of

Doctoral Thesis: Towards Effective Tools for Debugging Machine Learning Models

Julius Adebayo AbstractThis thesis addresses the challenge of detecting and fixing the errors of a machine learning (ML) model–model debugging. Current ML models, especially overparametrized deep neural networks