System lets robots identify an object’s properties through handling
With a novel simulation method, robots can guess the weight, softness, and other physical properties of an object just by picking it up.
New tool evaluates progress in reinforcement learning
“IntersectionZoo,” a benchmarking tool, uses a real-world traffic problem to test progress in deep reinforcement learning algorithms.
Novel AI model inspired by neural dynamics from the brain
New type of “state-space model” leverages principles of harmonic oscillators.
Designing a new way to optimize complex coordinated systems
Using diagrams to represent interactions in multipart systems can provide a faster way to design software improvements.
“Periodic table of machine learning” could fuel AI discovery
Researchers have created a unifying framework that can help scientists combine existing ideas to improve AI models or create new ones.
Making AI-generated code more accurate in any language
A new technique automatically guides an LLM toward outputs that adhere to the rules of whatever programming language or other format is being used.
A faster way to solve complex planning problems
By eliminating redundant computations, a new data-driven method can streamline processes like scheduling trains, routing delivery drivers, or assigning airline crews.
Training LLMs to self-detoxify their language
A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.
New method efficiently safeguards sensitive AI training data
The approach maintains an AI model’s accuracy while ensuring attackers can’t extract secret information.
Researchers teach LLMs to solve complex planning challenges
This new framework leverages a model’s reasoning abilities to create a “smart assistant” that finds the optimal solution to multistep problems.
Robotic helper making mistakes? Just nudge it in the right direction
New research could allow a person to correct a robot’s actions in real-time, using the kind of feedback they’d give another human.
Letterlocking: A new look at a centuries-old practice
A first history of the document security technology, co-authored by MIT Libraries’ Jana Dambrogio, provides new tools for interdisciplinary research.
Sometimes, when competitors collaborate, everybody wins
Engineers developed a planning tool that can help independent entities decide when they should invest in joint projects.
Rooftop panels, EV chargers, and smart thermostats could chip in to boost power grid resilience
MIT engineers propose a new “local electricity market” to tap into the power potential of homeowners’ grid-edge devices.
Like human brains, large language models reason about diverse data in a general way
A new study shows LLMs represent different data types based on their underlying meaning and reason about data in their dominant language.