
Twelve teams of students and postdocs across the MIT community presented innovative startup ideas with potential for real-world impact.

New method uses crowdsourced feedback to help train robots
Human Guided Exploration (HuGE) enables AI agents to learn quickly with some help from humans, even if the humans make mistakes.

A faster way to teach a robot
A new technique helps a nontechnical user understand why a robot failed, and then fine-tune it with minimal effort to perform a task effectively.

Selecting the right method gives users a more accurate picture of how their model is behaving, so they are better equipped to correctly interpret its predictions.

Learning to grow machine-learning models
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.

Efficient technique improves machine-learning models’ reliability
The method enables a model to determine its confidence in a prediction, while using no additional data and far fewer computing resources than other methods.

Putting a new spin on computer hardware
Luqiao Liu utilizes a quantum property known as electron spin to build low-power, high-performance computer memories and programmable computer chips.

A faster way to preserve privacy online
New research enables users to search for information without revealing their queries, based on a method that is 30 times faster than comparable prior techniques.

Models trained on synthetic data can be more accurate than other models in some cases, which could eliminate some privacy, copyright, and ethical concerns from using real data.

Expanding the MIT-IBM Watson AI Lab’s network of neurons
On October 6, nearly 50 undergraduate and graduate students and postdocs, primarily from MIT, attended the MIT-IBM Watson AI Lab’s networking event. The goal was to connect young…