Research
Research

Controlled diffusion model can change material properties in images

“Alchemist” system adjusts the material attributes of specific objects within images to potentially modify video game models to fit different environments, fine-tune VFX, and diversify robotic training.

Scientists use generative AI to answer complex questions in physics

A new technique that can automatically classify phases of physical systems could help scientists investigate novel materials.

Using ideas from game theory to improve the reliability of language models

A new “consensus game,” developed by MIT CSAIL researchers, elevates AI’s text comprehension and generation skills.

A better way to control shape-shifting soft robots

A new algorithm learns to squish, bend, or stretch a robot’s entire body to accomplish diverse tasks like avoiding obstacles or retrieving items.

HPI-MIT design research collaboration creates powerful teams

Together, the Hasso Plattner Institute and MIT are working toward novel solutions to the world’s problems as part of the Designing for Sustainability research program.

Natural language boosts LLM performance in coding, planning, and robotics

Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.

An AI dataset carves new paths to tornado detection

TorNet, a public artificial intelligence dataset, could help models reveal when and why tornadoes form, improving forecasters’ ability to issue warnings.

Mapping the brain pathways of visual memorability

For the first time, researchers use a combination of MEG and fMRI to map the spatio-temporal human brain dynamics of a visual image being recognized.

This tiny chip can safeguard user data while enabling efficient computing on a smartphone

Researchers have developed a security solution for power-hungry AI models that offers protection against two common attacks.

To build a better AI helper, start by modeling the irrational behavior of humans

A new technique can be used to predict the actions of human or AI agents who behave suboptimally while working toward unknown goals.