Scaling audio-visual learning without labels
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
A study inspired by the Japanese paper-cutting art provides a blueprint for designing shape-shifting materials and devices.
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.
Researchers develop an algorithm that decides when a “student” machine should follow its teacher, and when it should learn on its own.
Media Lab PhD students Manuj Dhariwal and Shruti Dhariwal introduce a new paradigm of creative collaboration in digital learning environments.
Undergraduate research helped feed physics and EECS major Thomas Bergamaschi’s post-MIT interest in tackling challenges.
Undergraduates whose research areas explore discrete math and neural networks honored for their academic achievements.
A two-day conference at MIT reflected on the impact of the Institute for Data, Systems, and Society since its launch, as founding Director Munther Dahleh prepares to step down.
The current MEng student is one of 175 students nationwide honored for nonpartisan democratic engagement work.
The machine-learning algorithm identified a compound that kills Acinetobacter baumannii, a bacterium that lurks in many hospital settings.
It’s more important than ever for artificial intelligence to estimate how accurately it is explaining data.
Violence Prevention and Response and the Institute Discrimination and Harassment Response Office celebrate students and employees for their efforts in combating sexual misconduct.
Researchers create a new simulation tool for robots to manipulate complex fluids in a step toward helping them more effortlessly assist with daily tasks.
By mapping the volumes of objects, rather than their surfaces, a new technique could yield solutions to computer graphics problems in animation and CAD.
Florian Chavagnat seeks to answer fundamental questions about heat transfer that will shape the success of nuclear power plants — and extended missions in space.